offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming
☆18Jun 2, 2025Updated last year
Alternatives and similar repositories for MTSA
Users that are interested in MTSA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Red Queen Dataset and data generation template☆29Dec 26, 2025Updated 8 months ago
- ☆27Mar 17, 2025Updated last year
- offical implementation of Jailbreak-R1☆15Jul 16, 2025Updated last year
- ☆21Apr 7, 2025Updated last year
- The official code for "Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks".☆19Jun 24, 2026Updated 2 months ago
- 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.
- [EMNLP 2025] Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking☆12Aug 22, 2025Updated last year
- Learning Safety Constraints for Large Language Models (ICML2025)☆35May 25, 2026Updated 3 months ago
- ☆19Oct 20, 2024Updated last year
- ☆30Aug 12, 2026Updated 2 weeks ago
- ☆67May 21, 2025Updated last year
- Agent3σ-Canary is an evaluation framework for AI Agent security in realistic runtime environments.☆35Aug 9, 2026Updated 3 weeks ago
- Official implementation of "TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards"☆32Jul 20, 2026Updated last month
- 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
- Code for "When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search" (NeurIPS 2024)☆18Oct 22, 2024Updated last year
- 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.
- ☆23Jul 26, 2025Updated last year
- An automated pipeline that leverages LLM's meta-learning capability to iteratively design and refine red-teaming systems without human in…☆30May 24, 2026Updated 3 months ago
- [AAAI 2026] This is the official implementation of the paper "ExtendAttack: Attacking Servers of LRMs via Extending Reasoning".☆26Mar 18, 2026Updated 5 months ago
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆89Feb 26, 2025Updated last year
- [NeurIPS 2025]: Personalized Safety in LLMs — A Benchmark and a Planning-Based Agent Approach☆18Oct 30, 2025Updated 9 months ago
- DARWIN is a self-evolving LLM jailbreak framework that grows a reusable strategy pool through external extraction, sandbox filtering, his…☆67Jun 5, 2026Updated 2 months ago
- A Framework for Evaluating AI Agent Safety in Realistic Environments☆38Aug 10, 2026Updated 2 weeks ago
- ☆24May 14, 2025Updated last year
- TRACE, a framework for turn-aware credit assignment for multi-turn jailbreak optimization☆22Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types☆26Nov 29, 2024Updated last year
- BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically i…☆46Mar 16, 2026Updated 5 months ago
- Emoji Attack [ICML 2025]☆45Jul 15, 2025Updated last year
- ☆33Jun 24, 2024Updated 2 years ago
- ☆40May 17, 2025Updated last year
- ☆32Feb 11, 2026Updated 6 months ago
- Solving the OpenAI Gym (MountainCarContinuous-v0) with DDPG☆21Jan 23, 2023Updated 3 years ago
- Adversarial Attack for Pre-trained Code Models☆10Jul 19, 2022Updated 4 years ago
- Official github repo for SafeDialBench, a comprehensive multi-turn dialogue benchmark to evaluate LLMs' safety.☆57May 12, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆122Apr 27, 2025Updated last year
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆30Jun 1, 2026Updated 2 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆60Oct 1, 2025Updated 10 months ago
- Official Implementation of "ToolSafe: Enhancing Tool Invocation Safety of LLM-based Agents via Proactive Step-level Guardrail and Feedbac…☆76Mar 25, 2026Updated 5 months ago
- Code for ICLR 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models☆37Jun 1, 2025Updated last year
- [ACL 2025] Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints☆19May 23, 2025Updated last year
- ☆30May 14, 2026Updated 3 months ago