Justin Phillips
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces an adversarial technique using genetic algorithms to deceive LLM-powered software reverse engineering agents, demonstrating that attackers can corrupt the analytical output of these systems by exploiting prompt injection vulnerabilities.
The paper introduces an adversarial technique using genetic algorithms to deceive LLM-powered software reverse engineering agents, demonstrating that attackers can corrupt the analytical output of automated binary analysis systems.
Papers
Automatically Attacking Software Reverse Engineering AI Agents
The paper introduces an adversarial technique using genetic algorithms to deceive LLM-powered software reverse engineering agents, demonstrating that attackers can corrupt the analytical output of the…