Linking pages
Linked pages
- [2307.15043] Universal and Transferable Adversarial Attacks on Aligned Language Models https://arxiv.org/abs/2307.15043 3 comments
- Broken Hill: A Productionized Greedy Coordinate Gradient… | Bishop Fox https://bishopfox.com/blog/brokenhill-attack-tool-largelanguagemodels-llm 1 comment
- GitHub - llm-attacks/llm-attacks: Universal and Transferable Attacks on Aligned Language Models https://github.com/llm-attacks/llm-attacks 0 comments
- GitHub - GraySwanAI/nanoGCG: A fast + lightweight implementation of the GCG algorithm in PyTorch https://github.com/GraySwanAI/nanoGCG 0 comments
Related searches:
Search whole site: site:github.com
Search title: GitHub - BishopFox/BrokenHill: A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)
See how to search.