offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming
☆16Jun 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☆26Dec 26, 2025Updated 6 months ago
- ☆27Mar 17, 2025Updated last year
- offical implementation of Jailbreak-R1☆15Jul 16, 2025Updated last year
- ☆20Apr 7, 2025Updated last year
- The official code for "Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks".☆18Jun 24, 2026Updated 3 weeks 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 10 months ago
- Learning Safety Constraints for Large Language Models (ICML2025)☆35May 25, 2026Updated last month
- ☆30Mar 20, 2024Updated 2 years ago
- ☆135Jun 29, 2026Updated 3 weeks ago
- Agent3σ-Canary is an evaluation framework for AI Agent security in realistic runtime environments.☆32Jun 24, 2026Updated 3 weeks ago
- Official implementation of "TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards"☆31Updated this week
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆24Jul 26, 2024Updated last year
- ☆22Jul 26, 2025Updated 11 months ago
- An automated pipeline that leverages LLM's meta-learning capability to iteratively design and refine red-teaming systems without human in…☆30May 24, 2026Updated last month
- 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.
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆89Feb 26, 2025Updated last year
- [AAAI 2026] This is the official implementation of the paper "ExtendAttack: Attacking Servers of LRMs via Extending Reasoning".☆25Mar 18, 2026Updated 4 months ago
- [NeurIPS 2025]: Personalized Safety in LLMs — A Benchmark and a Planning-Based Agent Approach☆16Oct 30, 2025Updated 8 months ago
- DARWIN is a self-evolving LLM jailbreak framework that grows a reusable strategy pool through external extraction, sandbox filtering, his…☆57Jun 5, 2026Updated last month
- A Framework for Evaluating AI Agent Safety in Realistic Environments☆38Oct 2, 2025Updated 9 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆61Oct 1, 2025Updated 9 months ago
- SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types☆26Nov 29, 2024Updated last year
- ☆23May 14, 2025Updated last year
- BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically i…☆42Mar 16, 2026Updated 4 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.
- Emoji Attack [ICML 2025]☆45Jul 15, 2025Updated last year
- ☆34Oct 14, 2021Updated 4 years ago
- ☆33Jun 24, 2024Updated 2 years ago
- ☆30Feb 11, 2026Updated 5 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
- ☆121Apr 27, 2025Updated last year
- ☆28Jun 13, 2026Updated last month
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆26Jun 1, 2026Updated last month
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆40May 17, 2025Updated last year
- 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
- ☆29May 14, 2026Updated 2 months ago
- ☆19Oct 20, 2024Updated last year
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆96May 9, 2025Updated last year
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆22May 6, 2025Updated last year