wangyu-ovo / MMLLinks
Code for the paper "Jailbreak Large Vision-Language Models Through Multi-Modal Linkage"
☆18Updated 10 months ago
Alternatives and similar repositories for MML
Users that are interested in MML are comparing it to the libraries listed below
Sorting:
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆29Updated 11 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆70Updated last year
- ☆35Updated 4 months ago
- ☆50Updated 9 months ago
- ☆52Updated last year
- ☆48Updated last year
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆173Updated 3 months ago
- Accepted by ECCV 2024☆156Updated 11 months ago
- ☆62Updated 6 months ago
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment☆23Updated 3 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…☆57Updated 6 months ago
- Accept by CVPR 2025 (highlight)☆18Updated 3 months ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆30Updated 9 months ago
- Repository for the Paper: Refusing Safe Prompts for Multi-modal Large Language Models☆18Updated 11 months ago
- [ICLR 2024] Towards Elminating Hard Label Constraints in Gradient Inverision Attacks☆13Updated last year
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆76Updated 4 months ago
- To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models☆32Updated 4 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆76Updated 8 months ago
- ☆65Updated 4 months ago
- Code for ICCV2025 paper——IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves☆14Updated 2 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆22Updated last year
- ☆37Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆36Updated 11 months ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆166Updated 3 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆18Updated 5 months ago
- [ECCV2024] Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajector…☆28Updated 10 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆23Updated 11 months ago
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbre…☆39Updated 3 months ago
- Welcome to the official repository for Siren, a project aimed at understanding and mitigating harmful behaviors in large language models …☆11Updated 3 weeks ago
- An implementation for MLLM oversensitivity evaluation☆14Updated 10 months ago