Alternatives and similar repositories for magic

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

• multimodalpragmatic / multimodalpragmatic
  ☆9Updated 3 weeks ago
• UCSC-VLAA / AttnGCG-attack
  ☆16Updated last month
• thu-coai / SafeUnlearning
  Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks
  ☆29Updated last year
• NUS-TRAIL / Unnatural_Language
  The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'
  ☆21Updated 2 months ago
• Jayfeather1024 / Backdoor-Enhanced-Alignment
  ☆20Updated 7 months ago
• ethz-spylab / rlhf-poisoning
  Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"
  ☆55Updated last year
• AI-safety-book / AI-safety-book.github.io
  ☆15Updated 5 months ago
• sail-sg / I-FSJ
  Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
  ☆62Updated 6 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…
  ☆20Updated 11 months ago
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆94Updated last year
• chenchenygu / watermark-learnability
  ☆25Updated 5 months ago
• David-Li0406 / AI-Supervision-Risk
  ☆21Updated 4 months ago
• papersPapers / BadPrompt
  Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"
  ☆38Updated last year
• thunxxx / MLLM-Jailbreak-evaluation-MMJ-Bench
  ☆52Updated 3 months ago
• XuandongZhao / weak-to-strong
  [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models
  ☆79Updated 2 months ago
• ThuCCSLab / misalignment
  [NDSS'25] The official implementation of safety misalignment.
  ☆15Updated 6 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"
  ☆81Updated last year
• pipilurj / MLLM-protector
  The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"
  ☆37Updated last year
• thu-coai / JailbreakDefense_GoalPriority
  [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
  ☆27Updated last year
• thu-ml / STAIR
  Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"
  ☆57Updated 4 months ago
• weizeming / momentum-attack-llm
  ☆21Updated 6 months ago
• zihao-ai / unthinking_vulnerability
  To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models
  ☆31Updated last month
• SORRY-Bench / sorry-bench
  Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)
  ☆56Updated 4 months ago
• umd-huang-lab / VLM-Poisoning
  Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"
  ☆50Updated 6 months ago
• Vaidehi99 / InfoDeletionAttacks
  ☆44Updated 5 months ago
• XuandongZhao / Unigram-Watermark
  [ICLR 2024] Provable Robust Watermarking for AI-Generated Text
  ☆33Updated last year
• sail-sg / AnyDoor
  AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models
  ☆55Updated last year
• deeplearning-wisc / picle
  Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)
  ☆25Updated last year
• princeton-nlp / benign-data-breaks-safety
  ☆41Updated 9 months ago
• llm-editing / editing-attack
  Code and dataset for the paper: "Can Editing LLMs Inject Harm?"
  ☆19Updated 8 months ago