May. 06, 2025
Piles of rare earth oxides praseodymium, cerium, lanthanum, neodymium, samarium and gadolinium. Peggy Greb/USDA-ARS

Every time you use your phone, open your computer or listen to your favorite music on AirPods, you are relying on critical minerals.

These materials are the tiny building blocks powering modern life. From lithium, cobalt, nickel and graphite in batteries to gallium in telecommunication systems that enable constant connectivity, critical minerals act as the essential vitamins of modern technology: small in volume but vital to function.

Yet the U.S. depends heavily on imports for most critical materials. In 2024 the U.S. imported 80% of rare earth elements it used, 100% of gallium and natural graphite, and 48% to 76% of lithium, nickel and cobalt, to name a few.

Read more »

May. 14, 2025
graphic of a research table

The School of Cybersecurity and Privacy at Georgia Tech is proud to recognize the accomplishments of five doctoral students who finished their doctoral programs in Spring 2025. These scholars have advanced critical research in software security, cryptography, and privacy, collectively publishing 34 papers, most of which appear in top-tier venues.

Ammar Askar developed new tools for software security in multi-language systems, including a concolic execution engine powered by large language models. He highlighted DEFCON 2021, which he attended with the Systems Software and Security Lab (SSLab), as a favorite memory.

Zhengxian He persevered through the pandemic to lead a major project with an industry partner, achieving strong research outcomes. He will be joining Amazon and fondly remembers watching sunsets from the CODA building.

Stanislav Peceny focused on secure multiparty computation (MPC), designing high-performance cryptographic protocols that improve efficiency by up to 1000x. He’s known for his creativity in both research and life, naming avocado trees after famous mathematicians and enjoying research discussions on the CODA rooftop.

Qinge Xie impressed faculty with her adaptability across multiple domains. Her advisor praised her independence and technical range, noting her ability to pivot seamlessly between complex research challenges.

Yibin Yang contributed to the advancement of zero-knowledge proofs and MPC, building toolchains that are faster and more usable than existing systems. His work earned a Distinguished Paper Award at ACM CCS 2023, and he also served as an RSAC Security Scholar. Yang enjoyed teaching and engaging with younger students, especially through events like Math Kangaroo.

Faculty mentors included Regents’ Entrepreneur Mustaque Ahamad, Professors Taesoo Kim and Vladimir Kolesnikov, and Assistant Professor Frank Li, who played vital roles in guiding the graduates’ research journeys.

Learn more about the graduates and their mentors on the 2025 Ph.D. graduate microsite.

News Contact

JP Popham, Communications Officer II

College of Computing | School of Cybersecurity and Privacy

May. 08, 2025
Cryptocurrency Illustration

Cryptocurrency Illustration

When the first cryptocurrency, Bitcoin, was proposed in 2008, the goal was simple: to create a digital currency free from banks and governments. Over time, that idea evolved into something much bigger: “decentralized finance,” or “DeFi.”

With decentralized finance, people trade, borrow and earn interest on crypto assets without relying on traditional intermediaries. DeFi services run on blockchains, which are essentially digital ledgers, and use “smart contracts” − self-executing code that automates financial transactions. Tens of billions of dollars have poured into the DeFi market.

But with innovation comes risks. The lack of centralized oversight has made crypto, including decentralized finance, a prime target for hackers and scammers. In 2024 alone, people lost nearly US$1.5 billion due to security exploits and fraud. And unlike traditional finance, there’s usually no way to recover stolen crypto.

As a computer scientist, I wanted to better understand how people perceive and respond to these risks. So my colleagues and I first conducted in-depth interviews with 14 crypto investors, then surveyed nearly 500 others to validate our findings.

Our study found that people often made the same mistakes, driven by recurring misconceptions and gaps in security awareness. Here are some of the most important.

Mistake 1: Thinking the blockchain guarantees security

Many people told us they thought decentralized finance was secure – but their reasoning wasn’t very convincing. Some seemed to confuse decentralized finance with blockchain technology itself, which is designed to ensure transactions are tamper-resistant through so-called “consensus mechanisms.” One told us that DeFi is secure “because a hacker would have to override an entire blockchain” to steal funds.

But services on the blockchain are still vulnerable to implementation and design flaws. These include smart contract breaches, in which bad guys exploit bugs in a service’s code, and front-end attacks, where a user interface is altered to redirect funds into a hacker’s wallet. A front-end attack was reportedly to blame for a recent $1.5 billion crypto heist.

CNBC reports on the record-breaking $1.5 billion crypto theft.

Mistake 2: Thinking safe keys mean safe funds

Another common misconception is that DeFi is secure if private keys are well stored. A private key is a secret code that allows someone to access their crypto assets. It’s true that in DeFi – unlike in centralized crypto finance where an exchange holds private keys – users have full control over their own private keys.

But even with perfect private key management, users can still lose funds by interacting with compromised DeFi platforms. That’s because safeguarding private keys can prevent only direct attacks targeting private key access, such as phishing attempts.

The people we spoke with also failed to follow best practices for securing their private keys. Using a hardware wallet – a physical device that stores private keys offline – is one of the most secure options for protecting keys from online threats. However, our study found that only a handful of participants actually used hardware wallets.

Mistake 3: Thinking 2-factor authentication is a silver bullet

Two-factor authentication, or 2FA, is a standard security mechanism in which two forms of verification are required to access an account. Think being texted a one-time code before you can log into your bank account.

To prevent account breaches, centralized crypto exchanges such as Binance and Coinbase use two-factor authentication for logins, account recovery and withdrawal confirmations. But while 2FA is crucial to security in the traditional and centralized crypto finance system, it plays a much smaller role in decentralized finance.

DeFi wallets give users access based on private key ownership rather than identity verification, which means traditional 2FA can’t be used. Instead, only 2FA-like mechanisms are available in DeFi. For instance, multisignature wallets require approval from multiple private key holders. However, if your private key is compromised, attackers can perform wallet operations on your behalf without any additional verification. In addition, even users who adopt 2FA-like measures can’t prevent the security breaches on the DeFi services’ end.

Unfortunately, our participants were overly confident regarding the effectiveness of 2FA, with one saying, “Two-factor authentication has been one of the best solutions for keeping wallets safe.” In our survey, 57.1% of users relied on 2FA as their only technical countermeasure against rug pulls – scams where project creators suddenly withdraw funds – and 49.3% did so for smart contract exploits. This misplaced trust could lead them to ignore more effective security strategies.

Mistake 4: Not managing token approvals

One such effective strategy is revoking token approvals. In DeFi, tokens are digital assets on a blockchain that represent value or rights, and users often need to approve smart contracts to access or spend them. But if you leave these approvals open, a malicious contract – or one that’s been hacked – can drain your wallet. So it’s crucial to routinely check all token approvals you’ve granted to prevent losses caused by fraudulent or hacked DeFi services. Specifically, you should limit spending allowances instead of using the default “unlimited” option, and revoke approvals for apps you no longer use or trust.

Worryingly, we found that only 10.8% and 16.3% of participants regularly checked and revoked token approvals to protect against rug pulls and smart contract exploits, respectively. In light of this, we recommend that wallet providers introduce a reminder feature to prompt users to review their token approvals periodically.

Mistake 5: Not learning from past incidents

Even after they’re hacked or scammed, people often don’t do anything to improve their security practices, we found. Just 17.6% of those who reported being victims of a DeFi scam regularly checked token approvals afterward. Worse, 26% took no action at all after a scam, and 16.4% doubled down by investing even more in other DeFi services.

Surprisingly, more than half of the victims said their belief in DeFi either stayed the same or grew stronger after the incident. One user who lost $4,700 due to a rug-pull incident said, “My belief in cryptocurrency has grown stronger after that because I made good money from it.” That person added, “An opportunity to make money is something I believe in.” This suggests that DeFi users’ financial motivations can sometimes outweigh their security concerns – and, perhaps, their better judgment.

There’s no one-size-fits-all solution to DeFi security. But awareness is the first step. To stay safe, crypto investors should use hardware wallets, revoke unused token approvals and continually learn new techniques to protect themselves from evolving threats. Most importantly, they should stay rational and not let the allure of profits cloud their security practices.The Conversation

 

This article is republished from The Conversation under a Creative Commons license. Read the original article.

News Contact

Author:

Mingyi Liu, Ph.D. student in Computer Science, Georgia Institute of Technology

Media Contact:

Shelley Wunder-Smith
shelley.wunder-smith@research.gatech.edu

May. 02, 2025
(Rendering: Second Bay Studios)

Jason Azoulay is an associate professor of Chemistry and Biochemistry and Materials Science and Engineering at Georgia Tech. He is the Georgia Research Alliance Vasser-Woolley Distinguished Investigator in Optoelectronics and serves as co-director of the Center for Organic Photonics and Electronics.

This story by Janette Neuwahl Tannen is shared jointly with the University of Miami newsroom. 

Today, most of us carry a fairly powerful computer in our hand — a smartphone.

But computers weren’t always so portable. Since the 1980s, they have become smaller, lighter, and better equipped to store and process vast troves of data.

Yet the silicon chips that power computers can only get so small.

“Over the past 50 years, the number of transistors we can put on a chip has doubled every two years,” says Kun Wang, assistant professor of physics at the University of Miami College of Arts and Sciences. “But we are rapidly reaching the physical limits for silicon-based electronics, and it’s more challenging to miniaturize electronic components using the technologies we have been using for half a century.”

It’s a problem that Wang and many in his field of molecular electronics are hoping to solve. Specifically, they are looking for a way to conduct electricity without using silicon or metal, which are used to create computer chips today. Using tiny molecular materials for functional components, like transistors, sensors, and interconnects in electronic chips offers several advantages, especially as traditional silicon-based technologies approach their physical and performance limits.

But finding the ideal chemical makeup for this molecule has stumped scientists. Recently, Wang, along with his graduate students, Mehrdad Shiri and Shaocheng Shen, and collaborators Jason Azoulay, associate professor at Georgia Institute of Technology and Georgia Research Alliance Vasser-Woolley Distinguished Investigator; and Ignacio Franco, professor at the University of Rochester, uncovered a promising solution.

This week, the team shared what they believe is the world’s most electrically conductive organic molecule. Their discovery, published in the Journal of the American Chemical Society, opens up new possibilities for constructing smaller, more powerful computing devices at the molecular scale. Even better, the molecule is composed of chemical elements found in nature — mostly carbon, sulfur, and nitrogen.

“So far, there is no molecular material that allows electrons to go across it without significant loss of conductivity,” Wang says. “This work is the first demonstration that organic molecules can allow electrons to migrate across it without any energy loss over several tens of nanometers.”

The testing and validation of their unique new molecule took more than two years.

However, the work of this team reveals that their molecules are stable under everyday ambient conditions and offer the highest possible electrical conductance at unparalleled lengths. Therefore, it could pave the way for classical computing devices to become smaller, more energy-efficient, as well as cost-efficient, Wang adds.

Currently, the ability of a molecule to conduct electrons decreases exponentially as the molecular size increases. These newly developed molecular “wires” are needed highways for information to be transferred, processed, and stored in future computing, Wang says.

“What’s unique in our molecular system is that electrons travel across the molecule like a bullet without energy loss, so it is theoretically the most efficient way of electron transport in any material system,” Wang notes. “Not only can it downsize future electronic devices, but its structure could also enable functions that were not even possible with silicon-based materials.”

Wang means that the molecule’s abilities might create new opportunities to revolutionize molecule-based quantum information science.

“The ultra-high electrical conductance observed in our molecules is a result of an intriguing interaction of electron spins at the two ends of the molecule,” he adds. “In the future, one could use this molecular system as a qubit, which is a fundamental unit for quantum computing.”

The team was able to notice these abilities by studying their new molecule under a scanning tunneling microscope (STM). Using a technique called STM break-junction, the team was able to capture a single molecule and measure its conductance.

Shiri, the graduate student, adds: “In terms of application, this molecule is a big leap toward real-world applications. Since it is chemically robust and air-stable, it could even be integrated with existing nanoelectronic components in a chip and work as an electronic wire or interconnects between chips.”

Beyond that, the materials needed to compose the molecule are inexpensive, and it can be created in a lab.

“This molecular system functions in a way that is not possible with current, conventional materials,” Wang says. “These are new properties that would not add to the cost but could make (computing devices) more powerful and energy efficient.” 

 

DOI: https://doi.org/10.1021/jacs.4c18150

Funding: U.S. Department of Energy, Office of Science, Basic Energy
Sciences; National Science Foundation (NSF); Air Force Office of Scientific Research (AFOSR) under support provided by the Organic Materials
Chemistry Program; Georgia Tech Research Institute (GTRI) Graduate
Student Researcher Fellowship Program (GSFP). Computational resources were provided by the Center for Integrated Research Computing (CIRC) at the
University of Rochester.

Along with Jason Azoulay, Georgia Tech co-authors also include Paramasivam Mahalingam, Tyler Bills, Alexander J. Bushnell, and Tanya A. Balandin.

News Contact

Jess Hunt-Ralston
Director of Communications 
College of Sciences at Georgia Tech

May. 02, 2025
Space Commercialization Panel

More than 100 researchers, faculty, industry representatives, alumni, and students came together on April 14 to explore the future of space research and exploration at the 2025 Yuri's Day Symposium. Hosted by Georgia Tech’s Space Research Initiative (SRI), Yuri’s Day serves as an annual celebration of space research across the Institute, the state of Georgia, and beyond. It built on the success of Yuri’s Day 2024, and was designed to be interactive and drive participation through panel discussions, a poster session, and networking opportunities.

The day began with opening remarks from Georgia Tech’s Executive Vice President of Research Tim Lieuwen, Vice President of Interdisciplinary Research Julia Kubanek, and the SRI executive committee, comprised of Professor Glenn Lightsey and Associate Professors Mariel Borowitz and Jennifer Glass. They provided an update on the SRI's latest achievements and its elevation to the Space Research Institute, one of Georgia Tech’s Interdisciplinary Research Institutes, on July 1.

“Space research is much broader than building spacecraft…it includes science, policy, business, and culture. We are here to celebrate all aspects of space research at Georgia Tech,” said Lightsey.

Borowitz lead a panel discussion on the implications of current space policies and the role of academic institutions in shaping the future of space exploration. It highlighted the importance of policy decisions in advancing space research and ensuring sustainable development. Jonathan Goldman, director of Quadrant-i at Georgia Tech, and his panel of entrepreneurs then discussed the commercialization of space technologies and the opportunities arising. They shared how collaboration between academia and industry can drive innovation and bring these new technologies to market.

The Georgia Tech Research Institute (GTRI) organized a space poster session during the lunch break to provide insight into the various space research projects happening there. This networking opportunity highlighted the breadth of work at GTRI and enabled researchers and students to present their projects to attendees. 

The Keynote speaker, Georgia Tech Alumnus Griff Russell, M.S. ME 1999, president of Gryphon Effect, LLC, and former SpaceX F9 vehicle manager, shared his personal journey to inspire future researchers. His talk, “From a letter to an astronaut to the trenches of Falcon 9 and beyond: Setting the foundation for accelerated Moon to Mars exploration” followed Russell’s path to the space industry, chronicling a letter he wrote to an astronaut early in his career to his current role as an entrepreneur. Russell shared his thoughts on the future of space exploration and encouraged students in the room to move fast and develop innovative new space technologies. “The time is now for you to make a difference,” he said. 

Professor Thom Orlando then led a panel of experts from other Georgia universities on the Human Space Initiative in the State of Georgia. Orlando and the panelists discussed the state's contributions to human spaceflight and the potential for future missions. This was followed by a panel on Earth analog field studies led by Assistant Professor Frances Rivera-Hernandez. Panelists including students explained how studying Earth analogs, like lava tubes and deserts, can help researchers better understand other planetary environments. Georgia Tech graduate students gave brief presentations chronicling recent fieldtrips and the data they gather in the field. The final session of the day led by Professor Lightsey showcased Georgia Tech’s space-related student organizations and the importance of engaging the next generation of scientists and engineers in space exploration.

As the Space Research Initiative transitions into the Space Research Institute, Georgia Tech is prepared to lead groundbreaking research, and Yuri’s Day gave attendees a preview of things to come. For more information about the SRI and the research at Georgia Tech, visit our website.

News Contact

Laurie Haigh
Research Communications

May. 01, 2025
Trenton Gantt and Hugh (Ka Yui) Chen work together in the lab

Early on, Georgia Tech graduate students William Trenton Gantt and Hugh (Ka Yui) Chen imagined working in the space industry.

“When I was 14, I dreamed about being in space one day,” recalls Chen, 22, a native of Hong Kong and a Ph.D. student in aerospace engineering. “I think the industry has been making space more accessible to everyone. Commercialization is a big part of enabling this.”

Gantt, an engineer and former U.S. Army veteran graduating with an MBA from the Scheller College of Business this spring, remembered seeing the space shuttle retire and companies begin privatizing space as he entered young adulthood. 

“I’ve always been interested in space, and a lot of it comes from the challenge of going to space,” he observes. “Seeing how hard it is to get to space and seeing it become achievable — that to me was the most attractive thing about it.”

For Gantt, the feeling always brings to mind John F. Kennedy’s famous line that spelled out America’s space ambitions: “We choose to go to the moon in this decade and do the other things, not because they are easy, but because they are hard.”

Recognizing Georgia Tech’s aerospace strengths, Gantt didn’t waste time building bridges within Scheller and in other parts of Georgia Tech. He founded the Scheller MBA Space Club, a first at the College, to track the industry as it grows and develops. 

“I came from a military background, so I had my eye on the defense industry going into the MBA program. Georgia Tech, being the No. 2 aerospace engineering undergraduate school in the nation, I knew they already had strong industry connections. Making connections was a big goal coming into this program.”

Assessing Early-Stage Space Tech 

He took part in the Entrepreneurship Assistants Program (EAP), which pairs a Scheller MBA student with a faculty or student inventor to evaluate early-stage technology for potential commercialization. He evaluated two space-related technologies, one with Chen’s support. 

“The EAs conduct technology commercialization assessments and develop a business model canvas. By applying an entrepreneurial strategy compass, they predict potential go-to-market strategies for new technology,” says Paul Joseph, principal in the Office of Commercialization’s Quadrant-i unit, who created the EAP.

 (See sidebar to read more about the EAP and the specific technologies assessed.)

Tapping Into a Nearly $2T Industry

According to McKinsey & Co., the space technology market, fueled by advancements in satellite technology, commercial space travel, and 5G networks, is projected to reach $1.8 trillion by 2035.

“We're seeing an industry shifting from a multibillion-dollar market cap to a multitrillion-dollar market cap in less than a decade. If you look at this from a business perspective, this is a massive addressable market for entrepreneurs," says Gantt.

From its Center for Space Technology and Research to the new Center for Space Policy and International Relations and labs like the Space Systems Design Lab, which focuses on areas such as CubeSat propulsion, lunar research, and hypersonic flight, Georgia Tech excels in space research across disciplines. In July, Georgia Tech will launch the Space Research Institute (SRI), one of its newest Interdisciplinary Research Institutes (IRI), to foster additional collaboration in this growing field.

“At Georgia Tech, there are competencies across every single College that will help to augment our understanding of space,” says Alex Oettl, professor of strategy and innovation in Scheller College, whose interest in the new space economy spans the last 20 years. “When you look at the technologies coming from Georgia Tech, they can impact this future trillion-dollar industry.”

 An economist by training, Oettl led Georgia Tech’s involvement in the Creative Destruction Lab-Atlanta, a multi-university program that helped commercialize early-stage scientific technologies.

Leveraging Affordable Launch

The emergence of affordable launch, spurred by SpaceX’s introduction of the Falcon 9 rocket using reusable rocket technology, has made space much more accessible, from biomedical companies to academic institutions.

“Because there has been a drop in the cost of accessing space, it allows experimentation to flourish,” says Oettl. 

He recalls Mark Costello, former chair of the Daniel Guggenheim School of Aerospace Engineering, explaining how he could launch a CubeSat into Low Earth Orbit out of his research budget, whereas before it would have been cost-prohibitive.

Today, Georgia Tech students and researchers are poised to capitalize on the new space economy stack — from new launch capabilities to new development in propellants and in-space operations and maintenance to more powerful sensors on Earth-observation satellites.

“I’ve seen firsthand the traction occurring on the commercial side. There are a lot of social scientists waking up to the opportunity that exists and thinking about business dynamics that will emerge as a result of this great opportunity,” he says.

Georgia Tech, an interdisciplinary, tech-focused university, brings significant capabilities across its Colleges to drive new and emerging technologies that have implications for space. 

“Space hits on all the strengths that exist at the various Colleges,” Oettl explains. “Faculty at Georgia Tech are pushing the boundary and showing our students innovations that will emerge in the space economy that are not immediately obvious — such as in adjacent industries.”

Oettl calls these first-order and spillover impacts of new technology. By first-order impacts, he means businesses can take advantage of these opportunities and create new products on top of the original innovation. By spillovers, he cites as an example an Earth-observation satellite enabling other industries to take advantage of data from the ground. For instance, insurance companies are one of the largest users of space technology by way of satellite imagery.

Bringing Capabilities Together Through New Space IRI

The SRI will bring together the best in engineering, computer science, policy, and business research across Georgia Tech. Along the way, it could help engineers and computer scientists think with a more business-minded approach to pitch their innovations to the commercial space sector. 

“You don’t see a lot of engineers having that inherent ability,” notes Gantt. “The Space IRI can shine by fostering collaboration between business students and engineers, enabling them to develop innovative go-to-market strategies and clearly define the unique value propositions these technologies offer to end users. You can bring these people together and create some forward momentum in the space industry.”

News Contact

News Contact: Laurie Haigh

Writer: Anne Wainscott-Sargent

May. 07, 2025
Man with crossed arms standing in a hallway with many windows

Mikkel Thomas has loved comic books since he was a kid, but he didn’t expect to relate to them as an adult. Just like Peter Parker didn’t intend to be a superhero, Thomas didn’t plan to be a research engineer. When he came to Georgia Tech in 1993 as an undergraduate, a bit of serendipity led him to the field of microelectronics (very small electronic components and circuits). Nearly three decades later, his superpower is demystifying the world of microelectronics for students.

Read more »

Apr. 30, 2025
Tesla crashes are only the most glaring of AI failures. South Jordan Police Department via APPEAR

Tesla crashes are only the most glaring of AI failures. South Jordan Police Department via APPEAR

From drones delivering medical supplies to digital assistants performing everyday tasks, AI-powered systems are becoming increasingly embedded in everyday life. The creators of these innovations promise transformative benefits. For some people, mainstream applications such as ChatGPT and Claude can seem like magic. But these systems are not magical, nor are they foolproof – they can and do regularly fail to work as intended.

AI systems can malfunction due to technical design flaws or biased training data. They can also suffer from vulnerabilities in their code, which can be exploited by malicious hackers. Isolating the cause of an AI failure is imperative for fixing the system.

But AI systems are typically opaque, even to their creators. The challenge is how to investigate AI systems after they fail or fall victim to attack. There are techniques for inspecting AI systems, but they require access to the AI system’s internal data. This access is not guaranteed, especially to forensic investigators called in to determine the cause of a proprietary AI system failure, making investigation impossible.

We are computer scientists who study digital forensics. Our team at the Georgia Institute of Technology has built a system, AI Psychiatry, or AIP, that can recreate the scenario in which an AI failed in order to determine what went wrong. The system addresses the challenges of AI forensics by recovering and “reanimating” a suspect AI model so it can be systematically tested.

Uncertainty of AI

Imagine a self-driving car veers off the road for no easily discernible reason and then crashes. Logs and sensor data might suggest that a faulty camera caused the AI to misinterpret a road sign as a command to swerve. After a mission-critical failure such as an autonomous vehicle crash, investigators need to determine exactly what caused the error.

Was the crash triggered by a malicious attack on the AI? In this hypothetical case, the camera’s faultiness could be the result of a security vulnerability or bug in its software that was exploited by a hacker. If investigators find such a vulnerability, they have to determine whether that caused the crash. But making that determination is no small feat.

Although there are forensic methods for recovering some evidence from failures of drones, autonomous vehicles and other so-called cyber-physical systems, none can capture the clues required to fully investigate the AI in that system. Advanced AIs can even update their decision-making – and consequently the clues – continuously, making it impossible to investigate the most up-to-date models with existing methods.

Researchers are working on making AI systems more transparent, but unless and until those efforts transform the field, there will be a need for forensics tools to at least understand AI failures.

Pathology for AI

AI Psychiatry applies a series of forensic algorithms to isolate the data behind the AI system’s decision-making. These pieces are then reassembled into a functional model that performs identically to the original model. Investigators can “reanimate” the AI in a controlled environment and test it with malicious inputs to see whether it exhibits harmful or hidden behaviors.

AI Psychiatry takes in as input a memory image, a snapshot of the bits and bytes loaded when the AI was operational. The memory image at the time of the crash in the autonomous vehicle scenario holds crucial clues about the internal state and decision-making processes of the AI controlling the vehicle. With AI Psychiatry, investigators can now lift the exact AI model from memory, dissect its bits and bytes, and load the model into a secure environment for testing.

Our team tested AI Psychiatry on 30 AI models, 24 of which were intentionally “backdoored” to produce incorrect outcomes under specific triggers. The system was successfully able to recover, rehost and test every model, including models commonly used in real-world scenarios such as street sign recognition in autonomous vehicles.

Thus far, our tests suggest that AI Psychiatry can effectively solve the digital mystery behind a failure such as an autonomous car crash that previously would have left more questions than answers. And if it does not find a vulnerability in the car’s AI system, AI Psychiatry allows investigators to rule out the AI and look for other causes such as a faulty camera.

Not Just for Autonomous Vehicles

AI Psychiatry’s main algorithm is generic: It focuses on the universal components that all AI models must have to make decisions. This makes our approach readily extendable to any AI models that use popular AI development frameworks. Anyone working to investigate a possible AI failure can use our system to assess a model without prior knowledge of its exact architecture.

Whether the AI is a bot that makes product recommendations or a system that guides autonomous drone fleets, AI Psychiatry can recover and rehost the AI for analysis. AI Psychiatry is entirely open source for any investigator to use.

AI Psychiatry can also serve as a valuable tool for conducting audits on AI systems before problems arise. With government agencies from law enforcement to child protective services integrating AI systems into their workflows, AI audits are becoming an increasingly common oversight requirement at the state level. With a tool like AI Psychiatry in hand, auditors can apply a consistent forensic methodology across diverse AI platforms and deployments.

In the long run, this will pay meaningful dividends both for the creators of AI systems and everyone affected by the tasks they perform.The Conversation

 

This article is republished from The Conversation under a Creative Commons license. Read the original article.

News Contact

Author:

David Oygenblik, Ph.D. Student in Electrical and Computer Engineering, Georgia Institute of Technology

Brendan Saltaformaggio, Associate Professor of Cybersecurity and Privacy, and Electrical and Computer Engineering, Georgia Institute of Technology

Media Contact:

Shelley Wunder-Smith
shelley.wunder-smith@research.gatech.edu

Apr. 28, 2025
From left to right, Jack Rose, Team Carchive; Angela Duodu, Hadley Williams,  Brandon Parker, Oluwatooni Alade , and Jesus Sierra Jr., Team Sensible; and  Yasmine Green, Team Onyc.

The winners of the 2025 Spring I2P Showcase, from left to right, Jack Rose, Team Carchive; Angela Duodu, Hadley Williams, Brandon Parker, Oluwatooni Alade , and Jesus Sierra Jr., Team Sensible; and Yasmine Green, Team Onyc.

At the Spring 2025 Idea to Prototype (I2P) Showcase, a prototype helping car enthusiasts find niche vehicles and their histories came out on top. Jack Rose, a junior in computer science, took home first place, a golden ticket to CREATE-X’s summer accelerator, Startup Launch, and advancement into the semifinal round of the InVenture Prize, a faculty-led innovation competition for undergraduate students and recent Tech bachelor’s graduates.

Second place was awarded to Team Sensible, made up of juniors Oluwatooni Alade, computer science; Brandon Parker, computer science; Angela Duodu, computer science; Jesus Sierra Jr., computer science; and Hadley Williams, computer engineering. Sensible is a browser extension that rates the sustainability of products users find online and offers alternative products for items that score low. 

Third place went to Team Onyc, which includes Yasmine Green, a first-year mechanical engineering student. Onyc replaces the computer mouse with a wearable alternative that allows users to control computer navigation with the movement of their fingertips and fingernails.

Dozens of teams competed at the showcase, which is the culmination of I2P, a CREATE-X course focused on supporting students in creating solutions. The course offers research credit (for undergraduates only), up to $500 in reimbursements for physical material expenses, the opportunity to work collaboratively across majors, and faculty mentorship. It is held in the spring, summer, and fall, and it’s open to undergraduate and graduate students from all majors.  

Read our Q&A with the winner and stay tuned for our interviews with the other winning teams.

Team Carchive

Jack Rose, Junior, Computer Science

Why did you pursue your startup? 

Rose: I’ve been into cars my whole life. Trying to track cars is my hobby. There are always edge cases, and how are you planning to attack them? Because I spent so much time, especially working with other people, getting this data, and trying to figure this out, I became very adept at understanding the data. The dealers, collectors especially, were trying to understand the whole story, so they would come to me. But the way I had to do it was spreadsheets all over the place, and I was trying to find a solution to keep it all in one spot. I couldn’t find a way to do it, so I said, “Well, I’ll build it.” And then I got into I2P.

What was challenging about building your prototype over the semester? 

Rose: This semester, it was mainly trying to come up with the schema and how to physically account for the edge cases. It’s not easy; it took a lot of deep thought, discussions with other people who are into these niche cars, and understanding what details we needed. I’m still trying to add more things and figure it out. It’s not perfect, but it’s enough.

What was your favorite part about I2P? 

Rose: Adding features that I was looking for. For example, let’s say I was looking for a car. Filter all the cars over 25 years old and imported to the U.S. — I can easily search my database.

What would you say to students who are interested in entrepreneurship? 

Rose: It’s always, “You should have started sooner.” I’ve always thought about it. My biggest advice is to just start doing it, even if it’s a little bit here, a little bit there. If it doesn’t work out, at least you’ve tried.

 

A photo gallery from the Spring 2025 I2P Showcase can be viewed on the CREATE-X Flickr page.

Students interested in the I2P program can register for the upcoming summer and fall semesters. The deadline for Summer 2025 is May 14, and the deadline for Fall 2025 is May 16.

CREATE-X's next event, Demo Day, will take place on Aug. 28 at Exhibition Hall, where more than 100 startups will be on display. Attendees can experience the newest batch of founders leveraging the latest technology to solve pressing challenges. The event offers an opportunity to network with entrepreneurs, industry leaders, and passionate enthusiasts, and supports the next generation of innovators. Register for Demo Day today and be a part of these founders’ journeys!  

 

News Contact

Breanna Durham

Marketing Strategist

Apr. 24, 2025
Instead of relying on traditional methods like cognitive tests and image scans, this new approach leverages data science and algorithms.

Instead of relying on traditional methods like cognitive tests and image scans, this new approach leverages data science and algorithms.

Md Abdur Rahaman

Ph.D. candidate Md Abdur Rahaman’s dissertation studies brain data to understand how changes in brain activity shape behavior.

Ph.D. candidate Md Abdur Rahaman’s dissertation studies brain data to understand how changes in brain activity shape behavior.

A Georgia Tech doctoral student’s dissertation could help physicians diagnose neuropsychiatric disorders, including schizophrenia, autism, and Alzheimer’s disease. The new approach leverages data science and algorithms instead of relying on traditional methods like cognitive tests and image scans.

Ph.D. candidate Md Abdur Rahaman’s dissertation studies brain data to understand how changes in brain activity shape behavior. 

Computational tools Rahaman developed for his dissertation look for informative patterns between the brain and behavior. Successful tests of his algorithms show promise to help doctors diagnose mental health disorders and design individualized treatment plans for patients.

“I've always been fascinated by the human brain and how it defines who we are,” Rahaman said. 

“The fact that so many people silently suffer from neuropsychiatric disorders, while our understanding of the brain remains limited, inspired me to develop tools that bring greater clarity to this complexity and offer hope through more compassionate, data-driven care.”

Rahaman’s dissertation introduces a framework focusing on granular factoring. This computing technique stratifies brain data into smaller, localized subgroups, making it easier for computers and researchers to study data and find meaningful patterns.

Granular factoring overcomes the challenges of size and heterogeneity in neurological data science. Brain data is obtained from neuroimaging, genomics, behavioral datasets, and other sources. The large size of each source makes it a challenge to study them individually, let alone analyze them simultaneously, to find hidden inferences. 

Rahaman’s research allows researchers and physicians to move past one-size-fits-all approaches. Instead of manually reviewing tests and scans, algorithms look for patterns and biomarkers in the subgroups that otherwise go undetected, especially ones that indicate neuropsychiatric disorders.

“My dissertation advances the frontiers of computational neuroscience by introducing scalable and interpretable models that navigate brain heterogeneity to reveal how neural dynamics shape behavior,” Rahaman said. 

“By uncovering subgroup-specific patterns, this work opens new directions for understanding brain function and enables more precise, personalized approaches to mental health care.”

Rahaman defended his dissertation on April 14, the final step in completing his Ph.D. in computational science and engineering. He will graduate on May 1 at Georgia Tech’s Ph.D. Commencement. 

After walking across the stage at McCamish Pavilion, Rahaman’s next step in his career is to go to Amazon, where he will work in the generative artificial intelligence (AI) field. 

Graduating from Georgia Tech is the summit of an educational trek spanning over a decade. Rahaman hails from Bangladesh where he graduated from Chittagong University of Engineering and Technology in 2013. He attained his master’s from the University of New Mexico in 2019 before starting at Georgia Tech. 

“Munna is an amazingly creative researcher,” said Vince Calhoun, Rahman’s advisor. Calhoun is the founding director of the Translational Research in Neuroimaging and Data Science Center (TReNDS).

TReNDS is a tri-institutional center spanning Georgia Tech, Georgia State University, and Emory University that develops analytic approaches and neuroinformatic tools. The center aims to translate the approaches into biomarkers that address areas of brain health and disease.    

“His work is moving the needle in our ability to leverage multiple sources of complex biological data to improve understanding of neuropsychiatric disorders that have a huge impact on an individual’s livelihood,” said Calhoun.

News Contact

Bryant Wine, Communications Officer
bryant.wine@cc.gatech.edu

Subscribe to Research Horizons