Search papers, labs, and topics across Lattice.
AutoEG is a multi-agent framework that automates exploit generation for black-box web applications by leveraging known third-party vulnerabilities. It addresses the challenges of precisely triggering vulnerabilities and adapting exploits to diverse deployments by first extracting vulnerability trigger logic from unstructured data and then iteratively refining exploits through feedback-driven interaction. Experiments on 104 real-world vulnerabilities demonstrate that AutoEG achieves an 82.41% success rate in exploitation, significantly surpassing existing state-of-the-art baselines.
Automatically exploiting web application vulnerabilities is now significantly more feasible, with AutoEG achieving over 80% success where previous methods struggled to reach 33%.
Large-scale web applications are widely deployed with complex third-party components, inheriting security risks arising from component vulnerabilities. Security assessment is therefore required to determine whether such known vulnerabilities remain practically exploitable in real applications. Penetration testing is a widely adopted approach that validates exploitability by launching concrete attacks against known vulnerabilities in real-world black-box systems. However, existing approaches often fail to automatically generate reliable exploits, limiting their effectiveness in practical security assessment. This limitation mainly stems from two issues: (1) precisely triggering vulnerabilities with correct technical details, and (2) adapting exploits to diverse real-world deployment settings. In this paper, we propose AutoEG, a fully automated multi-agent framework for exploit generation targeting black-box web applications. AutoEG has two phases: First, AutoEG extracts precise vulnerability trigger logic from unstructured vulnerability information and encapsulates it into reusable trigger functions. Second, AutoEG uses trigger functions for concrete attack objectives and iteratively refines exploits through feedback-driven interaction with the target application. We evaluate AutoEG on 104 real-world vulnerabilities with 29 attack objectives, resulting in 660 exploitation tasks and 55,440 exploit attempts. AutoEG achieves an average success rate of 82.41%, substantially outperforming state-of-the-art baselines, whose best performance reaches only 32.88%.
