Welcome to the official repository for Siren, a project aimed at understanding and mitigating harmful behaviors in large language models (LLMs). This repository contains the resources for reproducing the experiments described in our work.
☆15Jun 14, 2026Updated 4 months ago
Alternatives and similar repositories for siren
Users that are interested in siren are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆69May 21, 2025Updated last year
- Red Queen Dataset and data generation template☆29Dec 26, 2025Updated 9 months ago
- Official implementation of "TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards"☆32Sep 29, 2026Updated 2 weeks ago
- ☆39May 17, 2025Updated last year
- ☆26Mar 17, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆134Jul 29, 2026Updated 2 months ago
- The official code for "Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks".☆19Jun 24, 2026Updated 3 months ago
- ☆29May 14, 2025Updated last year
- The repo for using the model https://huggingface.co/thu-coai/Attacker-v0.1☆13Apr 23, 2025Updated last year
- ☆23Jul 26, 2025Updated last year
- 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
- Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)☆21Oct 22, 2024Updated last year
- [TMLR 2025] Official implementation of AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation☆27Jun 17, 2025Updated last year
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆88Nov 3, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆30Aug 12, 2026Updated 2 months ago
- This is the official repository for JailExpert☆22Sep 9, 2025Updated last year
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆35Dec 30, 2024Updated last year
- Auto1111 port of NVlab's adversarial purification method that uses the forward and reverse processes of diffusion models to remove advers…☆13Aug 8, 2023Updated 3 years ago
- ☆61May 30, 2024Updated 2 years ago
- ☆34Mar 16, 2025Updated last year
- ☆153Dec 3, 2025Updated 10 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆398Jan 23, 2025Updated last year
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆24Jul 26, 2024Updated 2 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆16May 2, 2026Updated 5 months ago
- [ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".☆182Aug 11, 2026Updated 2 months ago
- offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming☆18Jun 2, 2025Updated last year
- ☆39Jun 13, 2026Updated 4 months ago
- Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections☆23Jul 2, 2026Updated 3 months ago
- DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails☆34Feb 26, 2025Updated last year
- ☆21Apr 7, 2025Updated last year
- Code of paper: xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking"☆18Apr 3, 2026Updated 6 months ago
- ☆18Mar 25, 2026Updated 6 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- DSN jailbreak Attack & Evaluation Ensemble☆17Feb 7, 2026Updated 8 months ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆69Sep 12, 2026Updated last month
- [ACL 2025] Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints☆19May 23, 2025Updated last year
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆37Oct 15, 2023Updated 3 years ago
- Code for Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack(TPAMI 2025)☆42Aug 28, 2025Updated last year
- 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
- ☆25Jun 12, 2026Updated 4 months ago