sail-sg / Agent-Smith
[ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
☆93Updated 9 months ago
Alternatives and similar repositories for Agent-Smith:
Users that are interested in Agent-Smith are comparing it to the libraries listed below
- [Arxiv 2024] Dissecting Adversarial Robustness of Multimodal LM Agents☆54Updated this week
- Weak-to-Strong Jailbreaking on Large Language Models☆73Updated 10 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆53Updated last week
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆22Updated 6 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆116Updated last month
- [SafeGenAi @ NeurIPS 2024] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates☆67Updated 2 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆66Updated 10 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆112Updated 6 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆76Updated last year
- ☆52Updated 2 weeks ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆58Updated 11 months ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆67Updated 10 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆88Updated 7 months ago
- Flow of Reasoning: Training LLMs for Divergent Problem Solving with Minimal Examples☆57Updated this week
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆104Updated last month
- This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen,…☆44Updated last month
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆89Updated 3 weeks ago
- ☆21Updated 6 months ago
- ☆27Updated 11 months ago
- [ICML 2024 Oral] Official code repository for MLLM-as-a-Judge.☆62Updated last month
- ☆37Updated last month
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆92Updated 8 months ago
- [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use☆125Updated 9 months ago
- JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess …☆44Updated 6 months ago
- [EMNLP 2024] The official GitHub repo for the paper "Course-Correction: Safety Alignment Using Synthetic Preferences"☆19Updated 3 months ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆58Updated 2 weeks ago
- ☆158Updated last year
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆39Updated 2 months ago
- Official Code for Paper: Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆66Updated 3 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆65Updated 3 months ago