Popular repositories Loading

1. cybergym cybergym Public

   CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on real-world vulnerability analysis tasks.

   Python 569 67

2. Intuitor Intuitor Public

   [ICLR 2026] Learning to Reason without External Rewards

   Python 417 44

3. exploitgym exploitgym Public

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

   C 344 40

4. rl-generalization rl-generalization Public

   Modifiable OpenAI Gym environments for studying generalization in RL

   Python 90 14

5. verina verina Public

   Verina (Verifiable Code Generation Arena) is a high-quality benchmark enabling a comprehensive and modular evaluation of code, specification, and proof generation as well as their compositions.

   Lean 73 11

6. blackbox-attacks blackbox-attacks Public

   Code used in 'Exploring the Space of Black-box Attacks on Deep Neural Networks' (https://arxiv.org/abs/1712.09491)

   Python 63 13