SaFoLab-WISC / AdaShield
[ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting."
☆45Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for AdaShield
- JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess …☆35Updated 4 months ago
- Accepted by ECCV 2024☆74Updated last month
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆45Updated 3 months ago
- ☆20Updated last week
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆28Updated last month
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆108Updated 2 weeks ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆16Updated 2 weeks ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆67Updated 11 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆26Updated 5 months ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆44Updated 7 months ago
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆31Updated 7 months ago
- ☆23Updated 5 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆24Updated 9 months ago
- ☆30Updated 5 months ago
- ☆25Updated 4 months ago
- ☆37Updated 3 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆20Updated last month
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆15Updated 3 weeks ago
- [Arxiv 2024] Adversarial attacks on multimodal agents☆39Updated 4 months ago
- The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?☆19Updated 2 weeks ago
- [ICML 2024 Oral] Official code repository for MLLM-as-a-Judge.☆55Updated 3 months ago
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime☆37Updated last year
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systems☆161Updated last year
- Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆87Updated 6 months ago
- ☆34Updated 9 months ago
- The official code of the paper "Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate".☆80Updated 3 weeks ago
- [ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models☆99Updated last week
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Uns…☆58Updated 2 weeks ago
- ☆19Updated 3 weeks ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆14Updated 3 weeks ago