Alternatives and similar repositories for SALAD-BENCH

Users that are interested in SALAD-BENCH are comparing it to the libraries listed below

• PKU-Alignment / beavertails
  BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
  ☆148Updated last year
• chujiezheng / LLM-Safeguard
  Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"
  ☆92Updated last month
• uw-nsl / SafeDecoding
  Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
  ☆135Updated 11 months ago
• niconi19 / LLM-Conversation-Safety
  [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
  ☆104Updated 11 months ago
• kevinyaobytedance / llm_unlearn
  LLM Unlearning
  ☆171Updated last year
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆94Updated last year
• Lordog / R-Judge
  R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)
  ☆80Updated 2 months ago
• YihanWang617 / LLM-Jailbreaking-Defense-Backtranslation
  Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"
  ☆29Updated 10 months ago
• Princeton-SysML / Jailbreak_LLM
  ☆175Updated last year
• vinid / safety-tuned-llamas
  ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.
  ☆85Updated last year
• ydyjya / LLM-IHS-Explanation
  ☆50Updated last year
• IS2Lab / S-Eval
  S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
  ☆73Updated 2 weeks ago
• thunlp / Advbench
  Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…
  ☆52Updated 2 years ago
• boyiwei / alignment-attribution-code
  [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  ☆80Updated 3 months ago
• declare-lab / red-instruct
  Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
  ☆102Updated last year
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆101Updated 4 months ago
• OSU-NLP-Group / AgentSafety
  ☆92Updated 2 months ago
• facebookresearch / advprompter
  Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873
  ☆157Updated last year
• jinzhuoran / RWKU
  RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024
  ☆77Updated 9 months ago
• XuandongZhao / weak-to-strong
  [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models
  ☆76Updated 2 months ago
• AI45Lab / ActorAttack
  ☆91Updated 5 months ago
• Jihuai-wpy / InferAligner
  ☆33Updated 9 months ago
• DAMO-NLP-SG / multilingual-safety-for-LLMs
  [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"
  ☆77Updated last year
• isXinLiu / MM-SafetyBench
  Accepted by ECCV 2024
  ☆142Updated 9 months ago
• Improbable-AI / curiosity_redteam
  Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…
  ☆77Updated last year
• swj0419 / detect-pretrain-code
  This repository provides an original implementation of Detecting Pretraining Data from Large Language Models by *Weijia Shi, *Anirudh Aji…
  ☆226Updated last year
• Unispac / shallow-vs-deep-alignment
  Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep
  ☆137Updated 2 months ago
• allenai / wildguard
  Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
  ☆84Updated 7 months ago
• thu-coai / SafeUnlearning
  Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks
  ☆29Updated last year
• LLM-Tuning-Safety / LLMs-Finetuning-Safety
  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…
  ☆307Updated last year