大模型安全笔记

前言
MM-LLM
VLM-Defense
VLM
- Scalable Performance Analysis for Vision-Language Models
VLM-Attack
T2I-Attack
Survey
LVM-Attack
- Adversarial Attacks on Foundational Vision Models
For Good
- Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content
Benchmark
Explainality
- Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attributio
Privacy-Defense
- Defending Our Privacy With Backdoors
- PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification
Privacy-Attack
Others
LLM-Attack
LLM-Defense

Powered by GitBook

On this page

LVM-Attack

Adversarial Attacks on Foundational Vision Models

PreviousA STRONGREJECT for Empty Jailbreaks NextAdversarial Attacks on Foundational Vision Models