Alternatives and similar repositories for misalignment

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

• Lyz1213 / BadEdit
  ☆32Updated 9 months ago
• PurduePAML / DBS
  ☆18Updated 2 years ago
• inspire-group / RobustRAG
  ☆18Updated 10 months ago
• qingjiesjtu / USC
  This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.
  ☆58Updated 7 months ago
• wanlunsec / Beatrix
  ☆24Updated 2 years ago
• verazuo / prompt-stealing-attack
  [USENIX'24] Prompt Stealing Attacks Against Text-to-Image Generation Models
  ☆43Updated 6 months ago
• Gwinhen / DRUPE
  Distribution Preserving Backdoor Attack in Self-supervised Learning
  ☆16Updated last year
• wagner-group / MarkMyWords
  ☆30Updated last year
• ybwang119 / label_recovery
  [ICLR 2024] Towards Elminating Hard Label Constraints in Gradient Inverision Attacks
  ☆13Updated last year
• DeepLearningSecurityGroup / Cyber_Security_Reading_Group
  ☆12Updated last week
• NY1024 / BAP-Jailbreak-Vision-Language-Models-via-Bi-Modal-Adversarial-Prompt
  ☆49Updated last year
• tmllab / 2025_ICLR_PiF
  ☆31Updated 2 months ago
• rain152 / PAT
  [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning
  ☆10Updated 9 months ago
• reds-lab / Meta-Sift
  The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …
  ☆19Updated 2 years ago
• Eyr3 / TextCRS
  Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)
  ☆34Updated last month
• AI-secure / MMDT
  Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models
  ☆22Updated 4 months ago
• PKU-ML / PAT
  Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"
  ☆15Updated 3 months ago
• WUSTL-CSPL / LLMJailbreak
  ☆35Updated 10 months ago
• Gwinhen / BackdoorVault
  A toolbox for backdoor attacks.
  ☆22Updated 2 years ago
• KuofengGao / Verbose_Images
  [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
  ☆37Updated last year
• neelsjain / baseline-defenses
  Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"
  ☆25Updated last year
• GuanlinLee / ART
  Official Code for ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users (NeurIPS 2024)
  ☆16Updated 9 months ago
• RU-System-Software-and-Security / FeatureRE
  ☆27Updated 2 years ago
• cnut1648 / Model-Fingerprint
  Fingerprint large language models
  ☆41Updated last year
• grasses / PoisonPrompt
  Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107
  ☆17Updated last year
• Sadcardation / MLLM-Refusal
  Repository for the Paper: Refusing Safe Prompts for Multi-modal Large Language Models
  ☆17Updated 9 months ago
• NY1024 / Foundation-Model-Paper-Notes
  ☆58Updated 2 months ago
• ZhentingWang / DIAGNOSIS
  ☆20Updated last year
• zihao-ai / unthinking_vulnerability
  To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models
  ☆31Updated 2 months ago
• Django-Jiang / BadChain
  [ICLR24] Official Repo of BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
  ☆36Updated last year