uw-nsl / SafeDecodingLinks
Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
☆140Updated last year
Alternatives and similar repositories for SafeDecoding
Users that are interested in SafeDecoding are comparing it to the libraries listed below
Sorting:
- ☆180Updated last year
- ☆100Updated 6 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆94Updated 3 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆55Updated 10 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆158Updated 5 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆30Updated last year
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆159Updated last year
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆85Updated 3 months ago
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆317Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆103Updated last year
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…