sail-sg / Agent-Smith
[ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
☆90Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for Agent-Smith
- [Arxiv 2024] Adversarial attacks on multimodal agents☆39Updated 4 months ago
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆59Updated 3 months ago
- [SafeGenAi @ NeurIPS 2024] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates☆60Updated 3 weeks ago
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆62Updated 8 months ago
- ☆153Updated 11 months ago
- ☆91Updated 2 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆99Updated 4 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆106Updated last month
- ☆34Updated 9 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆48Updated 3 months ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆21Updated 4 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆67Updated 9 months ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆64Updated 8 months ago
- JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess …☆35Updated 4 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆84Updated 5 months ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆34Updated 3 weeks ago
- [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use☆115Updated 8 months ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆52Updated last month
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆43Updated 3 months ago
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆82Updated 6 months ago
- [ICML 2024 Oral] Official code repository for MLLM-as-a-Judge.☆55Updated 3 months ago
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆46Updated 3 months ago
- ☆27Updated 9 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆36Updated 2 months ago
- [ATTRIB @ NeurIPS 2024] When Attention Sink Emerges in Language Models: An Empirical View☆29Updated last month
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆28Updated last month
- Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆87Updated 6 months ago
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆110Updated 2 months ago
- ☆23Updated 6 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆122Updated 6 months ago