Vasilios Mavroudis
Scholar

Vasilios Mavroudis

Google Scholar ID: b10w74sAAAAJ
Research Scientist, Alan Turing Institute
Machine LearningSystems SecurityArtificial Intelligence
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
942
 
H-index
15
 
i10-index
22
 
Publications
20
 
Co-authors
15
list available
Contact
No contact links provided.
Publications
25 items
International AI Safety Report 2026
2026
Cited
6
SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity
2026
Cited
0
Beyond Rewards in Reinforcement Learning for Cyber Defence
2026
Cited
0
Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies
2026
Cited
0
Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse
2025
Cited
1
International AI Safety Report 2025: First Key Update: Capabilities and Risk Implications
2025
Cited
0
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
2025
Cited
0
What if we could hot swap our Biometrics?
2025
Cited
0
Resume (English only)
Co-authors
15 total
Florian Tramèr
Florian Tramèr
Assistant Professor of Computer Science, ETH Zurich
Inioluwa Deborah Raji
Inioluwa Deborah Raji
UC Berkeley
Co-author 3
Co-author 3
Yanick Fratantonio
Yanick Fratantonio
Senior Research Scientist, Google
Christopher Kruegel
Christopher Kruegel
University of California, Santa Barbara and Cisco, Inc.
Giovanni Vigna
Giovanni Vigna
UC Santa Barbara and VMware
George Danezis
George Danezis
Mysten Labs & University College London
Steven J. Murdoch
Steven J. Murdoch
Department of Computer Science, University College London