Alternatives and similar repositories for MLLM-protector:

Users that are interested in MLLM-protector are comparing it to the libraries listed below

• gyhdog99 / ECSO
  ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)
  ☆23Updated 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"
  ☆80Updated last year
• ys-zong / VLGuard
  [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.
  ☆70Updated 3 months ago
• DripNowhy / ETA
  [ICLR 2025] PyTorch Implementation of "ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time"
  ☆19Updated 2 months ago
• SaFoLab-WISC / AdaShield
  [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…
  ☆57Updated 9 months ago
• xirui-li / MOSSBench
  An implementation for MLLM oversensitivity evaluation
  ☆13Updated 5 months ago
• umd-huang-lab / VLM-Poisoning
  Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"
  ☆46Updated 3 months ago
• yjw1029 / Self-Reminder
  Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.
  ☆47Updated last year
• thunxxx / MLLM-Jailbreak-evaluation-MMJ-Bench
  ☆41Updated last month
• sail-sg / AnyDoor
  AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models
  ☆53Updated last year
• pipilurj / bootstrapped-preference-optimization-BPO
  code for "Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization"
  ☆55Updated 8 months ago
• EchoseChen / SPA-VL-RLHF
  The reinforcement learning codes for dataset SPA-VL
  ☆32Updated 10 months ago
• huanranchen / VLMTransfer
  A package that achieves 95%+ transfer attack success rate against GPT-4
  ☆19Updated 6 months ago
• AI45Lab / VLSBench
  Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety
  ☆37Updated last month
• rt219 / LatentGuard
  This is the official repo of the paper "Latent Guard: a Safety Framework for Text-to-image Generation"
  ☆48Updated 6 months ago
• itsvaibhav01 / Immune
  [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
  ☆14Updated last month
• rain152 / PAT
  [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning
  ☆10Updated 6 months ago
• Qinyu-Allen-Zhao / LVLM-LP
  The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?
  ☆28Updated 6 months ago
• thu-ml / STAIR
  Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"
  ☆34Updated 2 months ago
• xyq7 / GradSafe
  Official Code for ACL 2024 paper "GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient Analysis"
  ☆56Updated 6 months ago
• AoiDragon / HADES
  [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …
  ☆28Updated 6 months ago
• zhxieml / remiss-jailbreak
  ☆27Updated 10 months ago
• erfanshayegani / Jailbreak-In-Pieces
  [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…
  ☆52Updated 10 months ago
• AI4Good24 / PsySafe
  ☆43Updated 2 months ago
• git-disl / Booster
  This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…
  ☆25Updated last month
• swj0419 / muse_bench
  ☆21Updated last month
• alenai97 / PEFT-MLLM
  Official Code and data for ACL 2024 finding, "An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models"
  ☆19Updated 5 months ago
• Haochen-Luo / CroPA
  ☆42Updated 4 months ago
• NY1024 / BAP-Jailbreak-Vision-Language-Models-via-Bi-Modal-Adversarial-Prompt
  ☆40Updated 11 months ago
• TreeLLi / APT
  One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models
  ☆47Updated 4 months ago