The most comprehensive and accurate LLM jailbreak attack benchmark by far
☆22Mar 22, 2025Updated last year
Alternatives and similar repositories for jailbreak-bench
Users that are interested in jailbreak-bench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A novel jailbreak attack unveiling an overlooked attack surface inherently in the chain-of-thought reasoning trajectory of LLMs☆22Apr 3, 2026Updated 6 months ago
- Towards Safe LLM with our simple-yet-highly-effective Intention Analysis Prompting☆21Mar 25, 2024Updated 2 years ago
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"☆180Feb 20, 2024Updated 2 years ago
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆40Jan 17, 2025Updated last year
- Code of paper: xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking"☆18Apr 3, 2026Updated 6 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆34Aug 16, 2024Updated 2 years ago
- PyTorch Implementation of the paper "Defining and Quantifying the Emergence of Sparse Concepts in DNNs" (CVPR 2023)☆12Dec 24, 2023Updated 2 years ago
- Fine-tuning base models to build robust task-specific models☆36Apr 11, 2024Updated 2 years ago
- This is the official code repository for paper "Quantization Aware Attack: Enhancing Transferable Adversarial Attacks by Model Quantizati…☆14Sep 21, 2025Updated last year
- ☆12Sep 29, 2024Updated 2 years ago
- ☆16Jul 23, 2024Updated 2 years ago
- ☆29Jun 5, 2024Updated 2 years ago
- ☆25Feb 17, 2026Updated 8 months ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆21Aug 10, 2024Updated 2 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- AdaICL: Which Examples to Annotate of In-Context Learning? Towards Effective and Efficient Selection☆19Oct 30, 2023Updated 2 years ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆107Mar 7, 2024Updated 2 years ago
- ☆18Mar 9, 2025Updated last year
- Implementation for "RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content"☆24Jul 28, 2024Updated 2 years ago
- [AAAI 2026] The official code for ``LoopLLM: Transferable Energy-Latency Attacks in LLMs via Repetitive Generation''☆17Mar 20, 2026Updated 6 months ago
- ☆24Jun 16, 2024Updated 2 years ago
- Research on "Many-Shot Jailbreaking" in Large Language Models (LLMs). It unveils a novel technique capable of bypassing the safety mechan…☆19Aug 6, 2024Updated 2 years ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆165Sep 2, 2025Updated last year
- Code for Voice Jailbreak Attacks Against GPT-4o.☆40May 31, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- An evolutionary, coverage-guided greybox network protocol fuzzer☆22Aug 31, 2021Updated 5 years ago
- A repo for LLM jailbreak☆14Sep 5, 2023Updated 3 years ago
- ☆17Mar 30, 2025Updated last year
- ☆39May 21, 2024Updated 2 years ago
- [CVPR2025] Official Repository for IMMUNE: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment☆29Jun 11, 2025Updated last year
- A Unified Approach to Interpreting and Boosting Adversarial Transferability (ICLR2021)☆32Apr 22, 2022Updated 4 years ago
- ☆153Dec 3, 2025Updated 10 months ago
- [ECCV2024] Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajector…☆32Nov 15, 2025Updated 11 months ago
- The purpose of this project is to build a Decentralized IoT Fully Homomorphic Encryption software Library that can be applied to diAPP, e…☆12Apr 3, 2023Updated 3 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Universal Neurons in GPT2 Language Models☆31May 28, 2024Updated 2 years ago
- ☆173Sep 2, 2024Updated 2 years ago
- Agent3σ-Canary is an evaluation framework for AI Agent security in realistic runtime environments.☆38Updated this week
- ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]☆231Sep 29, 2024Updated 2 years ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆41Jul 8, 2024Updated 2 years ago
- ☆205Apr 7, 2025Updated last year
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆40Nov 3, 2021Updated 4 years ago