ASTRAL-Group / ASTRA
Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks"
☆15Updated 4 months ago
Alternatives and similar repositories for ASTRA:
Users that are interested in ASTRA are comparing it to the libraries listed below
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆51Updated 10 months ago
- ☆40Updated 10 months ago
- ☆38Updated 3 weeks ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆19Updated 6 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆19Updated 6 months ago
- ☆42Updated 4 months ago
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆17Updated last week
- ☆44Updated 8 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆55Updated last week
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆134Updated 2 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆46Updated 3 months ago
- An implementation for MLLM oversensitivity evaluation☆13Updated 5 months ago
- 🔥🔥🔥Breaking long thought processes of o1-like LLMs, such as DeepSeek-R1, QwQ☆28Updated last month
- ☆21Updated this week
- Accepted by ECCV 2024☆123Updated 6 months ago
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning☆10Updated 5 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆12Updated 5 months ago
- ☆51Updated 3 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…☆53Updated last month
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆24Updated 3 months ago
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment☆12Updated last month
- Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models☆18Updated last month
- ☆22Updated 7 months ago
- Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Generator, Gener…☆17Updated 6 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆33Updated last year
- Awesome Jailbreak, red teaming arxiv papers (Automatically Update Every 12th hours)☆26Updated this week
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆57Updated 9 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆23Updated 5 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆28Updated 6 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆69Updated 3 months ago