CRAIMay 28

Automatically Attacking Software Reverse Engineering AI Agents

arXiv:2605.3066713.4h-index: 2
Predicted impact top 34% in CR · last 90 daysOriginality Highly original
AI Analysis

This research identifies a new vulnerability for malware obfuscation in LLM-powered reverse engineering tools, which is critical for cybersecurity professionals and developers integrating LLMs into their toolchains.

This paper introduces an adversarial technique that uses genetic algorithm-based prompt generation to deceive LLM-powered disassembly and decompilation systems. The method corrupts the analytical output of these systems by misinterpreting binary executables, effectively bypassing automated detection systems.

Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analysts to safely conduct robust static analysis without having access to original source code. Coupled with the analytic power of large language models (LLM), agentic systems enabled with tools, such as GhidraMCP, can allow analysts to automate a previously human driven process. Although this automation can increase the productivity of a single malware analyst, it also introduces a new area of vulnerability for malware obfuscation. This paper presents an adversarial technique using genetic algorithm-based prompt generation, a modification of an adversarial attack known as AutoDAN, to demonstrate the ability to deceive LLM-powered disassembly and decompilation systems into misinterpreting binary executables, effectively corrupting their analytical output. This proof-of-concept methodology exploits inherent vulnerabilities in how LLMs process and interpret decompiled machine code via prompt injection by using extraneous string variable assignments to pass surreptitious instructions to the LLM while not impacting the functionality of the executable file. We demonstrate this capability through several concise examples. This approach could enable attackers to bypass automated detection systems that rely on LLM-driven analysis pipelines. By studying and understanding this attack, insights can be gained regarding the security implication of integrating LLMs into cybersecurity toolchains and building more robust agentic code analysis systems.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes