[CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks"
☆55Jul 5, 2025Updated 8 months ago
Alternatives and similar repositories for ASTRA
Users that are interested in ASTRA are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] PyTorch Implementation of "ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time"☆30Jul 20, 2025Updated 8 months ago
- [COLM 2025] JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model☆25Nov 25, 2025Updated 3 months ago
- ☆60Jun 5, 2024Updated last year
- ☆76Mar 30, 2025Updated 11 months ago
- SVIP: Towards Verifiable Inference of Open-Source Large Language Models☆14Jun 3, 2025Updated 9 months ago
- ☆25Mar 16, 2025Updated last year
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆32Dec 30, 2024Updated last year
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆23Jul 26, 2024Updated last year
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆72Feb 9, 2026Updated last month
- Repo for Bring Your Own Vision-Language-Action (VLA) model, arxiv 2024☆37Jan 22, 2025Updated last year
- A curated list of resources dedicated to the safety of Large Vision-Language Models. This repository aligns with our survey titled A Surv…☆197Feb 6, 2026Updated last month
- ACL 2025 (Main) HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States☆159Jun 8, 2025Updated 9 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆35Nov 2, 2024Updated last year
- Hyperbolic Safety-Aware Vision-Language Models. CVPR 2025☆30Apr 8, 2025Updated 11 months ago
- Code repository for the paper "Heuristic Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models"☆15Aug 7, 2025Updated 7 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆88May 9, 2025Updated 10 months ago
- [CVPR 2025] Official implementation for JOOD "Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy"☆22Jun 11, 2025Updated 9 months ago
- ☆68Sep 30, 2025Updated 5 months ago
- An implementation for MLLM oversensitivity evaluation☆18Nov 16, 2024Updated last year
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆37Jun 1, 2025Updated 9 months ago
- [ICLR 2025] Official codebase for the ICLR 2025 paper "Multimodal Situational Safety"☆32Jun 23, 2025Updated 8 months ago
- ☆58Jun 13, 2024Updated last year
- This is the official codebase for paper: Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Acti…☆41Feb 24, 2026Updated 3 weeks ago
- ☆23Jun 13, 2024Updated last year
- Accepted by ECCV 2024☆193Oct 15, 2024Updated last year
- (NeurIPS 2025) Official implementation for "MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?"☆47Jun 3, 2025Updated 9 months ago
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆31Nov 2, 2025Updated 4 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆176Apr 23, 2025Updated 10 months ago
- [ICLR'26] Official PyTorch implementation of "Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models".☆63Mar 5, 2026Updated 2 weeks ago
- [EMNLP 2025 Main] AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time☆88Jun 10, 2025Updated 9 months ago
- Fork of Microsoft/LightGBM to include support for the CEGB (Cost Efficient Gradient Boosting) algorithm. Original repository at https://g…☆13Jun 30, 2017Updated 8 years ago
- Transformer Model to detect deepfakes from popular datasets. Predictions made on embeddings (features) generated by a different ViT model…☆14Nov 27, 2023Updated 2 years ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆36Oct 23, 2024Updated last year
- Automatically Update LLM Papers Daily using Github Actions. Ref: https://github.com/Vincentqyw/cv-arxiv-daily☆10Updated this week
- Code and data for "ImgTrojan: Jailbreaking Vision-Language Models with ONE Image"☆24Mar 26, 2025Updated 11 months ago
- ☆67Jun 1, 2025Updated 9 months ago
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆45Apr 21, 2024Updated last year
- The code of the paper of "A Differentiable Semantic Metric Approximation in Probabilistic Embedding for Cross-Modal Retrieval" accepted b…☆19Jan 16, 2024Updated 2 years ago
- Official implementation of T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition☆21Oct 23, 2024Updated last year