Scholar
Dmitrii Volkov
Google Scholar ID: Wbf3J4cAAAAJ
Palisade Research
AI Safety
AI Security
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
40
H-index
3
i10-index
2
Publications
7
Co-authors
2
list available
Publications
7 items
Language Models Can Autonomously Hack and Self-Replicate
2026
Cited
0
GPT-5 at CTFs: Case Studies From Top-Tier Cybersecurity Events
2025
Cited
0
Misalignment Bounty: Crowdsourcing AI Agent Misbehavior
2025
Cited
0
Evaluating AI cyber capabilities with crowdsourced elicitation
2025
Cited
0
Demonstrating specification gaming in reasoning models
2025
Cited
0
Resurrecting saturated LLM benchmarks with adversarial encoding
2025
Cited
0
LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild
arXiv.org · 2024
Cited
0
Co-authors
2 total
Artem Petrov
Palisade Research
Christian Schroeder de Witt
University of Oxford
