Automatically Attacking Software Reverse Engineering AI Agents
European Conference on Cyber Warfare and Security · 15.06.2026 · 25 (1) · 199-205
DOI: 10.34190/eccws.25.1.4597 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Conference on Cyber Warfare and Security, online erschienen am 15.06.2026. Verfasst von Brian Crawford und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
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 decomplication 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.
Zitieren
APA
Crawford, B., Phillips, J., & McClure, P. (2026). Automatically Attacking Software Reverse Engineering AI Agents. European Conference on Cyber Warfare and Security, 25(1), 199-205. https://doi.org/10.34190/eccws.25.1.4597
Vancouver
Crawford B, Phillips J, McClure P. Automatically Attacking Software Reverse Engineering AI Agents. European Conference on Cyber Warfare and Security. 2026;25(1):199-205. doi:10.34190/eccws.25.1.4597
BibTeX
@article{Crawford2026,
author = {Crawford, Brian and Phillips, Justin and McClure, Patrick},
title = {Automatically Attacking Software Reverse Engineering AI Agents},
journal = {European Conference on Cyber Warfare and Security},
year = {2026},
volume = {25},
number = {1},
pages = {199--205},
doi = {10.34190/eccws.25.1.4597}
}
EUVIMED