[CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks"
☆60Jul 5, 2025Updated 9 months ago
Alternatives and similar repositories for ASTRA
Users that are interested in ASTRA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2025] PyTorch Implementation of "ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time"☆31Jul 20, 2025Updated 9 months ago
- ☆76Mar 30, 2025Updated last year
- ☆28Mar 16, 2025Updated last year
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment☆28Jun 11, 2025Updated 10 months ago
- Official implementation for "ALI-Agent: Assessing LLMs'Alignment with Human Values via Agent-based Evaluation"☆21Jan 31, 2026Updated 3 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆73Feb 9, 2026Updated 2 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆81Jun 6, 2024Updated 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…☆201Feb 6, 2026Updated 2 months ago
- ACL 2025 (Main) HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States☆164Jun 8, 2025Updated 10 months ago
- ☆25May 28, 2025Updated 11 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆36Nov 2, 2024Updated last year
- Röttger et al. (2025): "MSTS: A Multimodal Safety Test Suite for Vision-Language Models"☆17Mar 31, 2025Updated last year
- 😎 up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.☆538Apr 17, 2026Updated 2 weeks ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆89May 9, 2025Updated 11 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [CVPR 2025] Official implementation for JOOD "Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy"☆22Jun 11, 2025Updated 10 months ago
- ☆69Sep 30, 2025Updated 7 months ago
- Code repository for the paper "Heuristic Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models"☆17Aug 7, 2025Updated 8 months ago
- An implementation for MLLM oversensitivity evaluation☆18Nov 16, 2024Updated last year
- ☆40Jan 16, 2026Updated 3 months ago
- The loss landscape of Large Language Models resemble basin!☆37Jul 8, 2025Updated 9 months ago
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆36Jun 1, 2025Updated 10 months ago
- ☆60Jun 13, 2024Updated last year
- Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting☆17Apr 15, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- (NeurIPS 2025) Official implementation for "MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?"☆50Jun 3, 2025Updated 10 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆179Apr 23, 2025Updated last year
- [ICLR'26] Official PyTorch implementation of "Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models".☆64Mar 5, 2026Updated last month
- [EMNLP 2025 Main] AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time☆90Jun 10, 2025Updated 10 months ago
- [AAAI 2026] This is the official implementation of the paper "ExtendAttack: Attacking Servers of LRMs via Extending Reasoning".☆22Mar 18, 2026Updated last month
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆40Oct 17, 2024Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆35Oct 23, 2024Updated last year
- Code and data for "ImgTrojan: Jailbreaking Vision-Language Models with ONE Image"☆24Mar 26, 2025Updated last year
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆46Apr 21, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [NeurIPS 2025] Official Implementation for "Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding"☆22Dec 8, 2024Updated last year
- Official eval code for ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation☆27Dec 12, 2025Updated 4 months ago
- [ICML 2022] "Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness" by Tianlong Chen*, Huan Zhang*, Zhenyu Zhang, Shiyu…☆16Jun 22, 2022Updated 3 years ago
- On the Robustness of GUI Grounding Models Against Image Attacks☆12Apr 8, 2025Updated last year
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆202Jun 26, 2025Updated 10 months ago
- ☆10Nov 6, 2024Updated last year
- The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …☆61Apr 2, 2026Updated 3 weeks ago