KryptoPilot: 一种面向开放世界的知识增强型大语言模型代理用于自动化密码学利用
KryptoPilot: An Open-World Knowledge-Augmented LLM Agent for Automated Cryptographic Exploitation
AI总结：
KryptoPilot通过开放世界知识增强和受控推理，提升LLM在密码学CTF挑战中的自动化解决能力。
摘要：
捕获-the-Flag（CTF）竞赛在现代网络安全中扮演着核心角色，作为训练从业者和评估进攻性和防御性技术的平台，这些技术源于现实世界中的漏洞。尽管近年来在大语言模型（LLMs）方面取得了进展，但现有的基于LLM的代理在高难度的密码学CTF挑战中仍然无效，这些挑战需要精确的密码分析知识、稳定的长周期推理和有纪律地与专门工具链交互。通过系统性的探索性研究，我们证明，知识粒度不足，而非模型推理能力，是限制成功密码学利用的主要因素：粗略或抽象化的外部知识往往无法支持正确的攻击建模和实现。受此观察的启发，我们提出了KryptoPilot，一种面向开放世界的知识增强型LLM代理，用于自动化密码学利用。KryptoPilot通过深度研究流水线实现动态开放世界知识获取，一个用于结构化知识重用的持久工作区，以及一个通过行为约束和成本感知模型路由稳定推理的治理子系统。这种设计使知识对齐精确的同时保持了在异构子任务中的高效推理。我们对两个已建立的CTF基准和六个现实世界的CTF竞赛进行了评估。KryptoPilot在InterCode-CTF上实现了完全解决率，在NYU-CTF基准上解决了56至60%的密码学挑战，在现实竞赛中成功解决了33个密码学挑战中的26个，包括多个最早解决和唯一解决的实例。这些结果证明了开放世界、细粒度知识增强和受控推理对于扩展基于LLM的代理到现实世界密码学利用的必要性。
英文摘要：
Capture-the-Flag (CTF) competitions play a central role in modern cybersecurity as a platform for training practitioners and evaluating offensive and defensive techniques derived from real-world vulnerabilities. Despite recent advances in large language models (LLMs), existing LLM-based agents remain ineffective on high-difficulty cryptographic CTF challenges, which require precise cryptanalytic knowledge, stable long-horizon reasoning, and disciplined interaction with specialized toolchains. Through a systematic exploratory study, we show that insufficient knowledge granularity, rather than model reasoning capacity, is a primary factor limiting successful cryptographic exploitation: coarse or abstracted external knowledge often fails to support correct attack modeling and implementation. Motivated by this observation, we propose KryptoPilot, an open-world knowledge-augmented LLM agent for automated cryptographic exploitation. KryptoPilot integrates dynamic open-world knowledge acquisition via a Deep Research pipeline, a persistent workspace for structured knowledge reuse, and a governance subsystem that stabilizes reasoning through behavioral constraints and cost-aware model routing. This design enables precise knowledge alignment while maintaining efficient reasoning across heterogeneous subtasks. We evaluate KryptoPilot on two established CTF benchmarks and in six real-world CTF competitions. KryptoPilot achieves a complete solve rate on InterCode-CTF, solves between 56 and 60 percent of cryptographic challenges on the NYU-CTF benchmark, and successfully solves 26 out of 33 cryptographic challenges in live competitions, including multiple earliest-solved and uniquely-solved instances. These results demonstrate the necessity of open-world, fine-grained knowledge augmentation and governed reasoning for scaling LLM-based agents to real-world cryptographic exploitation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
