Sudhir Trivedi
Southern University and A & M College, LA·Computer Science
More than 2.5 million electric vehicles (EVs) now drive on U.S. roads, supported by over 70,000 charging stations.
- Fields
Computer Science
Engineering
- Topics
cybersecurity
electric vehicles
EV charging
- Grants
- 1 known grant, through Sep 2028
What they work on
- Identify and cluster Internet-connected EV management stations at scale using fingerprinting that combines automated web scraping, recursive unsupervised learning and pattern matching, and retrieve their firmware and software for analysis.
- Analyze the security of EVMS firmware and web endpoints with a machine-learning digital forensics method that combines static analysis, memory forensics, dynamic instrumentation and hypervisor introspection.
- Train large language models on a new instruction-based dataset, using supervised fine-tuning, reinforcement learning and transfer learning, to automatically detect vulnerabilities in EVMS source code and suggest code fixes.
- Build a large-scale threat repository, accessible through RESTful APIs and web interfaces, indexing discovered threat models, vulnerabilities and retrieved EVMS artifacts.
More about the research
These chargers are run by cloud-based EV management stations (EVMS), the online systems that handle charging, billing and user authentication. Because these systems are critical infrastructure, they have become targets for attacks, some state-sponsored, that exploit security weaknesses that have rarely been studied. This collaborative project, linking several Minority Serving Institutions with industry and government partners, aims to find, analyze and fix these vulnerabilities before attackers can use them.
Why it matters
Attacks on EV charging management systems could disrupt charging, billing and the wider electrified transportation network. By finding and disclosing vulnerabilities, automating code fixes with LLMs and sharing a public threat repository, this work could help EV operators, vendors and security researchers protect charging infrastructure.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Nasir Ghani
University of South Florida, FL·Computer Science
Identify and cluster internet-connected EV Management Stations (EVMS) using fingerprinting based on automated web scraping, recursive unsupervised learning and pattern matching, mapping their configurations and connections.
Jie Yan
Bowie State University, MD·Computer Science
Investigate the sources of hallucination — fabricated or inaccurate output — when large language models are applied to digital forensic casework, and develop techniques that reduce it enough for results to align with evidentiary standards.
Ramesh Karri
New York University, NY·Computer Science
Build a web infrastructure of virtual playgrounds where researchers share data, code and tools for studying cyberattacks on smart manufacturing machines and networks.
The school
Southern University and A & M College: 2 labs on PI Pages, $5M a year on research, 29 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.