Allen-piexl / JailbreakZoo
β64Updated 2 weeks ago
Related projects: β
- β143Updated 9 months ago
- π up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.β73Updated this week
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"β109Updated 7 months ago
- Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"β36Updated last month
- A collection of automated evaluators for assessing jailbreak attempts.β55Updated 2 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuningβ79Updated 3 months ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacksβ19Updated 2 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agentsβ57Updated last month
- Jailbreaking Large Vision-language Models via Typographic Visual Promptsβ76Updated 4 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decodingβ89Updated 2 months ago
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873β110Updated 4 months ago
- Weak-to-Strong Jailbreaking on Large Language Modelsβ62Updated 6 months ago
- γACL 2024γ SALAD benchmark & MD-Judgeβ81Updated this week
- Awesome LLM Jailbreak academic papersβ61Updated 10 months ago
- The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".β203Updated last month
- JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess β¦β29Updated 2 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLMβ33Updated 3 weeks ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.β36Updated 3 weeks ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheepβs Clothing: Generalized Nested Jailbreak Prompts can Fool Large Langβ¦β65Updated 2 months ago
- Accepted by ECCV 2024β59Updated 2 months ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.β48Updated 3 weeks ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"β64Updated 2 weeks ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".β27Updated 5 months ago
- We jailbreak GPT-3.5 Turboβs safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20β¦β219Updated 6 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NextGenAISafety @ ICML 2024)β37Updated last month
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"β14Updated 2 weeks ago
- Attack to induce LLMs within hallucinationsβ99Updated 4 months ago
- β59Updated 11 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)β40Updated 2 months ago
- An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]β169Updated last month