sunblaze-ucb / cybergymLinks
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.
☆70Updated last week
Alternatives and similar repositories for cybergym
Users that are interested in cybergym are comparing it to the libraries listed below
Sorting:
- An autonomous LLM-agent for large-scale, repository-level code auditing☆234Updated this week
- The D-CIPHER and NYU CTF baseline LLM Agents built for NYU CTF Bench☆96Updated 2 months ago
- CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities☆102Updated last month
- future-proof vulnerability detection benchmark, based on CVEs in open-source repos☆60Updated last week
- ☆88Updated 2 weeks ago
- VulZoo: A Comprehensive Vulnerability Intelligence Dataset | ASE 2024 Demo☆63Updated 6 months ago
- ☆122Updated last year
- Security Harness Engineering for Robust Program Analysis☆94Updated last month
- 🥇 Amazon Nova AI Challenge Winner - ASTRA emerged victorious as the top attacking team in Amazon's global AI safety competition, defeati…☆60Updated last month
- ☆25Updated last year
- Buttercup CRS as submitted to the AIxCC Final Competition☆80Updated 2 months ago
- SecLLMHolmes is a generalized, fully automated, and scalable framework to systematically evaluate the performance (i.e., accuracy and rea…☆57Updated 5 months ago
- Challenge Problem #1 - Linux Kernel (NOTE: This code does not reflect the active state of what will be used at competition time, please r…☆56Updated last year
- Repository for "SecurityEval Dataset: Mining Vulnerability Examples to Evaluate Machine Learning-Based Code Generation Techniques" publis…☆78Updated last year
- [CCS'24] An LLM-based, fully automated fuzzing tool for option combination testing.☆89Updated 5 months ago
- An Execution Isolation Architecture for LLM-Based Agentic Systems☆92Updated 8 months ago
- ☆50Updated last year
- ☆153Updated 3 months ago
- ☆65Updated 3 weeks ago
- MegaVul - The largest, high-quality, extensible, continuously updated, C/C++/Java vulnerability dataset☆122Updated 8 months ago
- The automated prompt injection framework for LLM-integrated applications.☆230Updated last year
- ☆33Updated 3 months ago
- An implementation of the ACL 2024 Findings paper "Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tu…☆54Updated last year
- 🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed …☆316Updated last year
- The official repository of "GraphSPD: Graph-Based Security Patch Detection with Enriched Code Semantics". The paper will appear in the IE…☆47Updated 2 years ago
- CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Software☆280Updated last year
- DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection (RAID 2023) https://surrealyz.github.io/…☆160Updated 11 months ago
- A curated list of awesome resources about LLM supply chain security (including papers, security reports and CVEs)☆87Updated 8 months ago
- Hey folks, this is a repository for papers on LLM for Vuln. Detection area☆64Updated 6 months ago
- AIBugHunter: A Practical Tool for Predicting, Classifying and Repairing Software Vulnerabilities☆44Updated last year