LLM驱动的智能系统在逆向工程中仍受限于混淆与架构复杂性。
Challenges and Future Directions in Agentic Reverse Engineering Systems
- 对比静态、动态与混合代理的逆向工程表现
- 发现令牌限制与代码混淆导致失败率高
- 适合安全研究者与系统设计者参考未来方向
基于大语言模型（LLMs）的智能体系统在复杂安全任务中日益普及，包括二进制逆向工程（RE）。尽管性能不断提升，当前系统在真实场景中仍面临挑战，尤其在涉及代码混淆、时序依赖和特殊架构的复杂场景下表现不佳。本文分析了现有智能体工具在静态、动态及混合模式下的使用情况，识别出若干关键局限：令牌数量限制、对代码混淆处理能力弱、缺乏程序约束机制。基于这些发现，本文系统梳理了当前挑战，并从安全角度提出未来系统设计应关注的方向。
原文摘要 · Abstract (English)
Agentic systems built on large language models (LLMs) are increasingly being used for complex security tasks, including binary reverse engineering (RE). Despite recent growth in popularity and capability, these systems continue to face limitations in realistic settings. Cutting-edge systems still fail in complex RE scenarios that involve obfuscation, timing, and unique architecture. In this work, we examine how agentic systems perform reverse engineering tasks with static, dynamic, and hybrid agents. Through an analysis of existing agentic tool usage, we identify several limitations, including token constraints, struggles with obfuscation, and a lack of program guardrails. From these findings, we outline current challenges and position future directions for system designers to overcome from a security perspective.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。