thu-ml / MLA-TrustLinks
A toolbox for benchmarking Multimodal LLM Agents trustworthiness across truthfulness, controllability, safety and privacy dimensions through 34 interactive tasks
☆50Updated 2 months ago
Alternatives and similar repositories for MLA-Trust
Users that are interested in MLA-Trust are comparing it to the libraries listed below
Sorting:
- Focused on the safety and security of Embodied AI☆57Updated 2 months ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆162Updated 2 months ago
- [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆48Updated last month
- Official repo of Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics☆34Updated 2 weeks ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆27Updated 10 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆67Updated last year
- ☆18Updated 9 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆63Updated last year
- To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models☆31Updated 3 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆38Updated last year
- Accepted by ECCV 2024☆149Updated 10 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…☆57Updated 5 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆23Updated 10 months ago
- ☆58Updated 5 months ago
- [ICML 2025] X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP☆27Updated 2 months ago
- ☆60Updated 3 months ago
- This is the official repository for the ICLR 2025 accepted paper Badrobot: Manipulating Embodied LLMs in the Physical World.☆31Updated 2 months ago
- ☆46Updated 8 months ago
- ☆102Updated last year
- ☆48Updated 6 months ago
- Codes for paper "SafeAgentBench: A Benchmark for Safe Task Planning of \\ Embodied LLM Agents"☆47Updated 6 months ago
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆68Updated 6 months ago
- Code and data for paper "Can Watermarked LLMs be Identified by Users via Crafted Prompts?" Accepted by ICLR 2025 (Spotlight)☆24Updated 8 months ago
- A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Models☆216Updated 3 weeks ago
- ☆47Updated last year
- ☆35Updated 3 months ago
- Code for ICCV2025 paper——IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves☆11Updated last month