PurCL / ASTRALinks
π₯ Amazon Nova AI Challenge Winner - ASTRA emerged victorious as the top attacking team in Amazon's global AI safety competition, defeating elite defending teams from universities worldwide in live adversarial evaluation.
β62Updated 2 months ago
Alternatives and similar repositories for ASTRA
Users that are interested in ASTRA are comparing it to the libraries listed below
Sorting:
- Official repo for FSE'24 paper "CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking"β16Updated 7 months ago
- An autonomous LLM-agent for large-scale, repository-level code auditingβ250Updated this week
- CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents onβ¦β83Updated 2 weeks ago
- β17Updated last year
- SecLLMHolmes is a generalized, fully automated, and scalable framework to systematically evaluate the performance (i.e., accuracy and reaβ¦β60Updated 5 months ago
- π₯π₯π₯ Detecting hidden backdoors in Large Language Models with only black-box accessβ45Updated 4 months ago
- CVE-Bench: A Benchmark for AI Agentsβ Ability to Exploit Real-World Web Application Vulnerabilitiesβ106Updated this week
- β25Updated last year
- β50Updated last year
- β123Updated last year
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agaiβ¦β52Updated 7 months ago
- Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Modelsβ20Updated last year
- β34Updated last year
- The D-CIPHER and NYU CTF baseline LLM Agents built for NYU CTF Benchβ99Updated this week
- β83Updated last year
- Parsing-based Analyzerβ51Updated 4 months ago
- [USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise aβ¦β108Updated last year
- The automated prompt injection framework for LLM-integrated applications.β235Updated last year
- A curated list of awesome resources about LLM supply chain security (including papers, security reports and CVEs)β87Updated 9 months ago
- [USENIX Security 25] PatchAgent is a LLM-based practical program repair agent that mimics human expertise.β97Updated this week
- Repository for "SecurityEval Dataset: Mining Vulnerability Examples to Evaluate Machine Learning-Based Code Generation Techniques" publisβ¦β80Updated last year
- Consuming Resrouce via Auto-generation for LLM-DoS Attack under Black-box Settingsβ17Updated last month
- β36Updated 4 months ago
- [CCS'24] An LLM-based, fully automated fuzzing tool for option combination testing.β91Updated 6 months ago
- β48Updated last year
- Binary Code Summarizationβ11Updated 6 months ago
- β91Updated last month
- β25Updated 2 years ago
- TensorFlow API analysis tool and malicious model detection toolβ35Updated 5 months ago
- β12Updated 5 months ago