Alternatives and similar repositories for JailDAM

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

• eric-ai-lab / MSSBench
  [ICLR 2025] Official codebase for the ICLR 2025 paper "Multimodal Situational Safety"
  ☆30Updated 5 months ago
• SaFoLab-WISC / FIUBench
  A Task of Fictitious Unlearning for VLMs
  ☆24Updated 7 months ago
• kigb / DropoutDecoding
  [NeurIPS 2025] Official Implementation for "Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding"
  ☆22Updated 11 months ago
• wicai24 / DOOR-Alignment
  ☆16Updated 7 months ago
• SaFoLab-WISC / AdaShield
  [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…
  ☆68Updated last year
• 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
• ExplainableML / sae-for-vlm
  [NeurIPS 2025] Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
  ☆43Updated 7 months ago
• luka-group / vlm-knowledge-conflict
  Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."
  ☆48Updated last year
• clemneo / llava-interp
  ☆73Updated last year
• nishadsinghi / CleanCLIP
  Official PyTorch implementation of "CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning" @ ICCV 2023
  ☆39Updated last month
• Qinyu-Allen-Zhao / LVLM-LP
  The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?
  ☆41Updated last year
• 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
• sail-sg / Meta-Unlearning
  ☆33Updated 7 months ago
• YiyangZhou / CSR
  [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models
  ☆80Updated last month
• gyhdog99 / ECSO
  ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)
  ☆34Updated last year
• MajorDavidZhang / MCL
  code for Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning
  ☆18Updated last year
• zycheiheihei / Transferable-Visual-Prompting
  [CVPR2024 Highlight] Official implementation for Transferable Visual Prompting. The paper "Exploring the Transferability of Visual Prompt…
  ☆46Updated 11 months ago
• s-vco / s-vco
  Symmetrical Visual Contrastive Optimization: Aligning Vision-Language Models with Minimal Contrastive Images
  ☆16Updated 5 months ago
• ZhentingWang / DUMP
  ☆32Updated 6 months ago
• ChnQ / TracingLLM
  ☆30Updated last year
• itsvaibhav01 / Immune
  [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
  ☆25Updated 5 months ago
• Dongping-Chen / MLLM-Judge
  [ICML 2024 Oral] Official code repository for MLLM-as-a-Judge.
  ☆86Updated 9 months ago
• haonan3 / V1
  V1: Toward Multimodal Reasoning by Designing Auxiliary Task
  ☆36Updated 7 months ago
• nickjiang2378 / vlm-hallucinations
  [ICLR '25] Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations"
  ☆92Updated 6 months ago
• UCSC-VLAA / STAR-1
  [AAAI'26 Oral] Official Implementation of STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
  ☆32Updated 7 months ago
• alchemistyzz / PeRL
  [NeurIPS'25] The official code of "PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning"
  ☆25Updated 2 months ago
• jiaangli / VLCA
  Do Vision and Language Models Share Concepts? A Vector Space Alignment Study
  ☆16Updated last year
• gyhdog99 / RACRO2
  Official PyTorch implementation of RACRO (https://www.arxiv.org/abs/2506.04559)
  ☆19Updated 4 months ago
• OpenCausaLab / CELLO
  ☆21Updated last year
• pipilurj / MLLM-protector
  The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"
  ☆44Updated last year