How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
This is the official source code for "SmoothLLM: Defending LLMs Against Jailbreaking Attacks" by Alex Robey, Eric Wong, Hamed Hassani, and George J. Pappas. To learn more about our work, see our blog post.
This is a repository for replicating the experiments from our paper: Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning .
This repository contains code for the paper Certifying LLM Safety against Adversarial Prompting.
RAIN is an innovative inference method that, by integrating self-evaluation and rewind mechanisms, enables frozen large language models to directly produce responses consistent with human preferences without requiring additional alignment data or model fine-tuning, thereby offering an effective…
The main features of safeailab/rain are: Defense Strategies, Self-Improvement Methods.
Projects with overlapping indexed features include: arobey1/smooth-llm — This is the official source code for "SmoothLLM: Defending LLMs Against Jailbreaking Attacks" by Alex Robey, Eric… chuhac/reasoning-to-defend — Code for paper. crystaleye42/eval-safety — This is a repository for replicating the experiments from our paper: Pruning for Protection: Increasing Jailbreak… damo-nlp-sg/multilingual-safety-for-llms — 📄 Paper • 🤗 Dataset. devoallen/indust — We have reorganized INDust, aligning evidence with three types of inductive instructions and implementing stricter… aounon/certified-llm-safety — This repository contains code for the paper Certifying LLM Safety against Adversarial Prompting.
