Alternatives and similar repositories for magic

Users that are interested in magic are comparing it to the libraries listed below

• UCSC-VLAA / AttnGCG-attack
  ☆20Updated 5 months ago
• AI-safety-book / AI-safety-book.github.io
  ☆19Updated 9 months ago
• weizeming / momentum-attack-llm
  ☆23Updated 10 months ago
• NUS-TRAIL / Unnatural_Language
  The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'
  ☆23Updated 6 months ago
• sail-sg / I-FSJ
  Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
  ☆65Updated 10 months ago
• Jayfeather1024 / Backdoor-Enhanced-Alignment
  ☆23Updated 11 months ago
• UCSC-VLAA / vllm-safety-benchmark
  [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"
  ☆84Updated 2 years ago
• David-Li0406 / AI-Supervision-Risk
  ☆21Updated 8 months ago
• clearloveclearlove / BEAT
  ☆14Updated 9 months ago
• Alibaba-AAIG / Oyster
  The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …
  ☆56Updated 2 months ago
• ybwang119 / Awesome-reasoning-safety
  This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL
  ☆52Updated 2 months ago
• yuplin2333 / representation-space-jailbreak
  Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…
  ☆22Updated last year
• weichen-yu / LM-Extraction
  ☆43Updated 2 years ago
• ethz-spylab / rlhf-poisoning
  Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"
  ☆62Updated last year
• llm-editing / editing-attack
  Code and dataset for the paper: "Can Editing LLMs Inject Harm?"
  ☆21Updated last year
• JasonForJoy / Model-Editing-Hurt
  EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
  ☆37Updated 6 months ago
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆98Updated last year
• XuandongZhao / weak-to-strong
  [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models
  ☆89Updated 6 months ago
• DYR1 / MoGU
  Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.
  ☆18Updated 10 months ago
• Vaidehi99 / InfoDeletionAttacks
  ☆48Updated 9 months ago
• thu-coai / SafeUnlearning
  Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks
  ☆32Updated last year
• poloclub / llm-landscape
  NeurIPS'24 - LLM Safety Landscape
  ☆33Updated last month
• papersPapers / BadPrompt
  Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"
  ☆40Updated last year
• wicai24 / DOOR-Alignment
  ☆16Updated 7 months ago
• mireshghallah / neighborhood-curvature-mia
  ☆23Updated 2 years ago
• princeton-nlp / benign-data-breaks-safety
  ☆41Updated last year
• thunxxx / MLLM-Jailbreak-evaluation-MMJ-Bench
  ☆66Updated 7 months ago
• zhxieml / remiss-jailbreak
  ☆33Updated last year
• alphadl / SafeLLM_with_IntentionAnalysis
  Towards Safe LLM with our simple-yet-highly-effective Intention Analysis Prompting
  ☆18Updated last year
• SALT-NLP / PopupAttack
  Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups
  ☆47Updated 11 months ago