Official implementation of "TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards"
☆32Sep 29, 2026Updated 2 weeks ago
Alternatives and similar repositories for TROJail
Users that are interested in TROJail are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Welcome to the official repository for Siren, a project aimed at understanding and mitigating harmful behaviors in large language models …☆15Jun 14, 2026Updated 4 months ago
- ☆69May 21, 2025Updated last year
- ☆26Mar 17, 2025Updated last year
- The official code for "Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks".☆19Jun 24, 2026Updated 3 months ago
- ☆18Mar 25, 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.
- ☆26Dec 18, 2025Updated 9 months ago
- PIForge: An Open Framework for RL-based Prompt Injection Red Teaming.☆35Sep 30, 2026Updated 2 weeks ago
- offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming☆18Jun 2, 2025Updated last year
- [CVPR2025] Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters☆44Mar 11, 2025Updated last year
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆39Jul 31, 2026Updated 2 months ago
- [🏆ECCV'26] Official Repo for SlowBA: An efficiency backdoor attack towards VLM-based GUI agents☆20Oct 3, 2026Updated last week
- ☆39May 17, 2025Updated last year
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆16May 2, 2026Updated 5 months ago
- [TMLR 2025] Official implementation of AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation☆27Jun 17, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆29May 14, 2025Updated last year
- ☆25Jun 12, 2026Updated 4 months ago
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆47Jun 1, 2026Updated 4 months ago
- ☆14Mar 11, 2025Updated last year
- [S&P 2026] SoK: Evaluating Jailbreak Guardrails for Large Language Models☆50Dec 17, 2025Updated 9 months ago
- [NeurIPS'25 Spotlight] Fine-grained List-wise Alignment for Generative Medication Recommendation☆18May 19, 2026Updated 4 months ago
- SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement☆79Jun 11, 2026Updated 4 months ago
- This is the official repository for JailExpert☆22Sep 9, 2025Updated last year
- Code for paper "MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM safety"☆58Oct 1, 2026Updated last week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [ACL 2025] iAgent: LLM Agent as a Shield between User and Recommender Systems☆37May 23, 2025Updated last year
- Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections☆23Jul 2, 2026Updated 3 months ago
- ☆134Jul 29, 2026Updated 2 months ago
- ☆16Sep 20, 2022Updated 4 years ago
- Repo for my blogs explaining swish activation function☆13Dec 17, 2017Updated 8 years ago
- TRACE, a framework for turn-aware credit assignment for multi-turn jailbreak optimization☆22Aug 26, 2026Updated last month
- Code and models for ``Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify Framework (ACL 2022)''☆12Jun 29, 2022Updated 4 years ago
- ☆13Feb 25, 2025Updated last year
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆22Mar 22, 2026Updated 6 months ago
- 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.
- ☆22Jan 26, 2024Updated 2 years ago
- [ACL 2025] Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints☆19May 23, 2025Updated last year
- [ICML 2026] Official implementations of ``SafeSearch: Automated Red-Teaming of LLM-Based Search Agents''☆19Mar 25, 2026Updated 6 months ago
- ☆56May 19, 2026Updated 4 months ago
- [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments☆65Feb 9, 2026Updated 8 months ago
- [ICML 2025] Official code of "DAMA: Data- and Model-aware Alignment of Multi-modal LLMs"☆16May 24, 2025Updated last year
- Solving the OpenAI Gym (MountainCarContinuous-v0) with DDPG☆21Jan 23, 2023Updated 3 years ago