Nasir Ghani
University of South Florida, FL·Computer Science
Electric vehicles (EVs) depend on a nationwide network of chargers, and that network is run by cloud-based software. More than 2.5 million EVs and over 70,000 charging stations in the U.S.
- 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 (EVMS) using fingerprinting based on automated web scraping, recursive unsupervised learning and pattern matching, mapping their configurations and connections.
- Analyze the security of EVMS firmware and web endpoints with a digital forensics method built on ensemble machine-learning classifiers, memory forensics, dynamic instrumentation and hypervisor introspection.
- Fine-tune large language models (LLMs) on a new instruction-based dataset to automatically detect vulnerabilities in EVMS source code and propose sound code fixes.
- Build a large-scale threat repository, accessible through RESTful APIs and web interfaces, that indexes discovered threat models, vulnerabilities and retrieved EVMS artifacts.
More about the research
rely on EV Management Stations (EVMS), online systems that handle charging, billing and user authentication. Because these systems are critical, they attract malicious attacks, some state-sponsored, that exploit weaknesses rarely studied before. This collaborative project aims to find and fix these security weaknesses before attackers can use them.
Why it matters
Attacks on EV charging-management systems could disrupt charging, billing and authentication for millions of drivers and threaten an electrified transportation sector central to the U.S. economy. Mapping these systems, finding their weaknesses, using AI to suggest code fixes and sharing a public threat repository could help EV operators, vendors and security researchers protect this infrastructure.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Sudhir Trivedi
Southern University and A & M College, LA·Computer Science
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.
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.
Yueqi Chen
University of Colorado Boulder, CO·Computer Science
Refactor the Community Earth System Model (CESM) codebase by decoupling its computational and control logic and rewriting the control layer in Python, so that modern security practices can be integrated.
The school
University of South Florida: 20 labs on PI Pages, $522M a year on research, 305 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.