Alternatives and similar repositories for magic

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

• UCSC-VLAA / AttnGCG-attack
  ☆23Updated 7 months ago
• weizeming / momentum-attack-llm
  ☆23Updated last year
• AI-safety-book / AI-safety-book.github.io
  ☆24Updated 11 months ago
• Jayfeather1024 / Backdoor-Enhanced-Alignment
  ☆24Updated last year
• thu-coai / SafeUnlearning
  Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks
  ☆32Updated last year
• Vaidehi99 / InfoDeletionAttacks
  ☆48Updated last year
• clearloveclearlove / BEAT
  ☆14Updated 11 months ago
• David-Li0406 / AI-Supervision-Risk
  ☆21Updated 10 months ago
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆98Updated last year
• 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…
  ☆23Updated last year
• which47 / LLMCL
  Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning
  ☆36Updated last year
• yjw1029 / Self-Reminder-Data
  Data for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder"
  ☆20Updated 2 years ago
• real-absolute-AI / Unnatural_Language
  The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'
  ☆24Updated 8 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"
  ☆86Updated 2 years ago
• ybwang119 / Awesome-reasoning-safety
  This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL
  ☆59Updated 5 months ago
• sail-sg / I-FSJ
  Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
  ☆65Updated last year
• ethz-spylab / rlhf-poisoning
  Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"
  ☆66Updated last year
• princeton-nlp / benign-data-breaks-safety
  ☆44Updated last year
• vfleaking / PTST
  Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"
  ☆22Updated 4 months ago
• keven980716 / weak-to-strong-deception
  [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"
  ☆13Updated last year
• stanford-crfm / air-bench-2024
  AIR-Bench 2024 is a safety benchmark that aligns with emerging government regulations and company policies
  ☆28Updated last year
• sail-sg / MMCBench
  ☆27Updated 2 years ago
• SALT-NLP / PopupAttack
  Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups
  ☆50Updated last year
• zhxieml / remiss-jailbreak
  ☆33Updated last year
• THU-KEG / SafetyNeuron
  Data and code for the paper: Finding Safety Neurons in Large Language Models
  ☆20Updated last week
• AI-secure / PolyGuard
  ☆16Updated 7 months ago
• JasonForJoy / Model-Editing-Hurt
  EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
  ☆38Updated 8 months ago
• ChnQ / TracingLLM
  ☆30Updated last year
• JTWang2000 / FreeShap
  Fine-tuning-free Shapley value (FreeShap) for instance attribution
  ☆14Updated last year
• papersPapers / BadPrompt
  Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"
  ☆40Updated last year