UCSC-VLAA / vllm-safety-benchmark
[ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"
☆75Updated last year
Alternatives and similar repositories for vllm-safety-benchmark:
Users that are interested in vllm-safety-benchmark are comparing it to the libraries listed below
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆55Updated last month
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆48Updated 10 months ago
- Accepted by ECCV 2024☆97Updated 4 months ago
- ☆27Updated 2 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆71Updated 7 months ago
- ☆30Updated 7 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆41Updated last month
- Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"☆18Updated 4 months ago
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆33Updated 10 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆22Updated 4 months ago
- [Arxiv 2024] Dissecting Adversarial Robustness of Multimodal LM Agents☆60Updated last month
- The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?☆25Updated 3 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆21Updated 3 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆38Updated 8 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆50Updated 7 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆46Updated 7 months ago
- ☆34Updated 2 months ago
- The reinforcement learning codes for dataset SPA-VL☆28Updated 7 months ago
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆52Updated 4 months ago
- ☆39Updated last week
- ☆14Updated 4 months ago
- ☆27Updated last year
- A package that achieves 95%+ transfer attack success rate against GPT-4☆17Updated 3 months ago
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆67Updated 4 months ago
- Official codebase for Image Hijacks: Adversarial Images can Control Generative Models at Runtime☆43Updated last year
- [FCS'24] LVLM Safety paper☆17Updated last month
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆23Updated 7 months ago
- ☆20Updated 7 months ago
- ☆30Updated 4 months ago