thu-ml / MMTrustEval
A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust)
β88Updated last week
Related projects: β
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systemsβ147Updated 10 months ago
- π up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.β73Updated this week
- β84Updated 7 months ago
- Accepted by ECCV 2024β59Updated 2 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shiβ¦β34Updated 2 months ago
- Improved techniques for optimization-based jailbreaking on large language modelsβ33Updated 3 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.β36Updated 3 weeks ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Modelsβ39Updated 5 months ago
- Accepted by IJCAI-24 Survey Trackβ117Updated 3 weeks ago
- JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess β¦β29Updated 2 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"β61Updated 9 months ago
- Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ76Updated 4 months ago
- β30Updated last month
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β14Updated 3 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β29Updated 8 months ago
- β24Updated 3 months ago
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Modelsβ156Updated 4 months ago
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]β45Updated last year
- β35Updated last year
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ17Updated 7 months ago
- Code for the paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β21Updated 6 months ago
- β62Updated 7 months ago
- official PyTorch implement of Towards Adversarial Attack on Vision-Language Pre-training Modelsβ45Updated last year
- The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsβ¦β43Updated last month
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Modelsβ31Updated 4 months ago
- β54Updated last month
- β28Updated 7 months ago
- [NeurIPS'2023] Official Code Repo:Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllabilityβ78Updated 10 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)β40Updated 2 months ago
- The official repository for paper "MLLM-Protector: Ensuring MLLMβs Safety without Hurting Performance"β30Updated 5 months ago