Official implementation of "TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards"
☆31Jul 20, 2026Updated this week
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 last month
- ☆67May 21, 2025Updated last year
- ☆27Mar 17, 2025Updated last year
- The official code for "Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks".☆18Jun 24, 2026Updated last month
- ☆17Mar 25, 2026Updated 4 months 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.
- PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses☆22Jul 17, 2026Updated last week
- Red Queen Dataset and data generation template☆27Dec 26, 2025Updated 6 months ago
- ☆32Mar 16, 2025Updated last year
- offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming☆16Jun 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…☆29Jul 6, 2026Updated 2 weeks ago
- [🏆ECCV'26] Official Repo for SlowBA: An efficiency backdoor attack towards VLM-based GUI agents☆15Jul 1, 2026Updated 3 weeks ago
- ☆40May 17, 2025Updated last year
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆15May 2, 2026Updated 2 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [TMLR 2025] Official implementation of AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation☆27Jun 17, 2025Updated last year
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆27Jun 1, 2026Updated last month
- ☆23May 14, 2025Updated last year
- ☆20Jun 12, 2026Updated last month
- [S&P 2026] SoK: Evaluating Jailbreak Guardrails for Large Language Models☆44Dec 17, 2025Updated 7 months ago
- ☆14Mar 11, 2025Updated last year
- ☆15May 19, 2026Updated 2 months ago
- SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement☆73Jun 11, 2026Updated last month
- This is the official repository for JailExpert☆23Sep 9, 2025Updated 10 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Code for paper "MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM safety"☆51May 11, 2026Updated 2 months ago
- [ACL 2025] iAgent: LLM Agent as a Shield between User and Recommender Systems☆34May 23, 2025Updated last year
- Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections☆21Jul 2, 2026Updated 3 weeks ago
- ☆134Jun 29, 2026Updated 3 weeks ago
- Code of paper: xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking"☆17Apr 3, 2026Updated 3 months ago
- The baseline method for CCIR 22 https://www.datafountain.cn/competitions/573☆13Aug 2, 2022Updated 3 years ago
- RNN-based IDS for SOME/IP Intrusion Detection☆10Jul 20, 2021Updated 5 years ago
- DSN jailbreak Attack & Evaluation Ensemble☆17Feb 7, 2026Updated 5 months ago
- ☆16Sep 20, 2022Updated 3 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.
- Code and models for ``Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify Framework (ACL 2022)''☆12Jun 29, 2022Updated 4 years ago
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆20Mar 22, 2026Updated 4 months ago
- ☆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 4 months ago
- ☆52May 19, 2026Updated 2 months ago
- A Security Benchmark for Claude Code Agent Skills☆69Updated this week