A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)
☆174Jun 27, 2025Updated 8 months ago
Alternatives and similar repositories for MMTrustEval
Users that are interested in MMTrustEval are comparing it to the libraries listed below
Sorting:
- Accepted by ECCV 2024☆192Oct 15, 2024Updated last year
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆88Feb 26, 2025Updated last year
- ☆25Nov 4, 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
- Unified Adversarial Patch for Cross-modal Attacks in the Physical World (ICCV, 2023)☆46Dec 15, 2023Updated 2 years ago
- ☆72Mar 30, 2025Updated 11 months ago
- The official implementation for "Towards Transferable Targeted 3D Adversarial Attack in the Physical World" (CVPR, 2024))☆42Aug 6, 2024Updated last year
- ☆109Feb 16, 2024Updated 2 years ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆192Jun 26, 2025Updated 8 months ago
- [CVPR2024 Highlight] Official implementation for Transferable Visual Prompting. The paper "Exploring the Transferability of Visual Prompt…☆46Dec 20, 2024Updated last year
- [MICCAI 2025] Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in Histopathology☆12Jun 17, 2025Updated 8 months ago
- An implementation for MLLM oversensitivity evaluation☆17Nov 16, 2024Updated last year
- [CVPR2024 Highlight] Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning☆19Jun 14, 2024Updated last year
- Accepted by IJCAI-24 Survey Track☆231Aug 25, 2024Updated last year
- ☆44Jun 19, 2025Updated 8 months ago
- ☆58Aug 11, 2024Updated last year
- Physically Adversarial Infrared Patches with Learnable Shapes and Locations☆42Aug 13, 2023Updated 2 years ago
- ☆59Jun 5, 2024Updated last year
- [TACL] Do Vision and Language Models Share Concepts? A Vector Space Alignment Study☆16Nov 22, 2024Updated last year
- A list of research towards security&privacy in AI-Generated Content☆16Jan 10, 2025Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆38Oct 17, 2024Updated last year
- Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models☆266May 13, 2024Updated last year
- We introduce new approach, Token Reduction using CLIP Metric (TRIM), aimed at improving the efficiency of MLLMs without sacrificing their…☆20Jan 11, 2026Updated last month
- 😎 up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.☆505Feb 17, 2026Updated 2 weeks ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆31Dec 30, 2024Updated last year
- A Novel Semantic Segmentation Network using Enhanced Boundaries in Cluttered Scenes (WACV 2025)☆11Aug 11, 2025Updated 6 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆86Nov 28, 2023Updated 2 years ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆35Nov 2, 2024Updated last year
- [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆54Jul 21, 2025Updated 7 months ago
- ☆122Feb 3, 2025Updated last year
- ☆21Aug 19, 2024Updated last year
- [ICLR 2025] Official codebase for the ICLR 2025 paper "Multimodal Situational Safety"☆30Jun 23, 2025Updated 8 months ago
- Code for ISSTA'21 paper 'Attack as Defense: Characterizing Adversarial Examples using Robustness'.☆12Sep 4, 2021Updated 4 years ago
- ☆14Oct 6, 2024Updated last year
- The first toolkit for MLRM safety evaluation, providing unified interface for mainstream models, datasets, and jailbreaking methods!☆14Apr 8, 2025Updated 10 months ago
- [CVPR'24] HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(…☆329Oct 14, 2025Updated 4 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆80Jun 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 …☆59Sep 11, 2025Updated 5 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 9 months ago