umd-huang-lab / VLM-PoisoningLinks
Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"
☆51Updated 6 months ago
Alternatives and similar repositories for VLM-Poisoning
Users that are interested in VLM-Poisoning are comparing it to the libraries listed below
Sorting:
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆81Updated last year
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆55Updated last year
- Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models☆22Updated 4 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆65Updated last year
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆73Updated 6 months ago
- ☆24Updated 5 months ago
- ☆55Updated 4 months ago
- ☆102Updated last year
- A package that achieves 95%+ transfer attack success rate against GPT-4☆23Updated 9 months ago
- ☆22Updated 8 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆62Updated last year
- ☆37Updated last year
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆98Updated 5 months ago
- Accepted by ECCV 2024☆147Updated 9 months ago
- ☆49Updated last year
- ☆31Updated 2 months ago
- Awesome Large Reasoning Model(LRM) Safety.This repository is used to collect security-related research on large reasoning models such as …☆68Updated last week
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment☆22Updated last month
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆160Updated last month
- Repository for the Paper: Refusing Safe Prompts for Multi-modal Large Language Models☆17Updated 9 months ago
- ☆46Updated 8 months ago
- To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models☆31Updated 2 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆26Updated 9 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆75Updated 3 months ago
- [NeurIPS-2023] Annual Conference on Neural Information Processing Systems☆209Updated 7 months ago
- ☆49Updated 11 months ago
- ☆17Updated 4 months ago
- ☆24Updated 11 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆29Updated 9 months ago
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆38Updated last year