
exploitgym
ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

This study analyzes Python pickle deserialization vulnerabilities, focusing on CVE-2024-3568 in Hugging Face Transformers' TFAutoModel. We reproduce…

Collection of CVE(work) on tenserflow binary pwning it

Exploits for CVE-2024-14027 creating using AI/Claude as a test.

A PoC for CVE-2024-3660. Arbitrary Code Execution in Keras.

Proof-of-concept exploit for CVE-2025-32434, a pickle deserialization vulnerability in PyTorch's weights_only mode, demonstrating malicious tar file…

Reproducible AI-assisted vulnerability rediscovery of CVE-2026-42945 in nginx, including technical analysis, PoC trigger, and patch validation for…

Evaluation framework for studying LLM agents that automatically generate working exploits from vulnerability reports, bypassing modern security…

Technical webinars on reverse engineering, malware analysis, and software protection.

Official repository for CTFTiny

Ethical, network-isolated Docker lab reproducing CVE-2026-26030 — Semantic Kernel in-memory vector store filter eval() RCE (patched in 1.39.4)

LlamaStack-RCE: Deterministic Supply Chain Exploitation & Hardening Framework [CVE-2024-50050] Focus on AI Security Research…

CVE-2025-31337 Security Advisory - Critical Buffer Overflow in AI Chatbot Framework