AI RESEARCH
Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents
arXiv CS.AI
•
ArXi:2605.30677v1 Announce Type: cross Agentic software reverse engineering systems are vulnerable to prompt injection attacks placed into the source code of executable binary files. This research nstrates defensive tactics for detecting the presences of prompt injection strings in the decompiler output of adversarial example programs. Methods for obfuscating these attacks and subsequent methods for defending against these obfuscations are also explored.