In offensive-LLM agent papers, dual-use risk is acknowledged in 39% of papers but concrete mitigations appear in only 7%.
Getting pwn’d by ai: Penetration testing with large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Recognition Without Mitigation: Ethical Frameworks in Autonomous Offensive-LLM Agent Research
In offensive-LLM agent papers, dual-use risk is acknowledged in 39% of papers but concrete mitigations appear in only 7%.