SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
☆20Aug 4, 2026Updated 2 months ago
Alternatives and similar repositories for SHE
Users that are interested in SHE are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Survey: The Path to Recursive Self-Improving Agents: Foundation, Framework, and Future Directions☆54Aug 27, 2026Updated last month
- The repo for paper: Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models.☆15Dec 16, 2024Updated last year
- Implementation of SLIM, a framework of dynamics skill lifecycle management for agentic reinforcement learning☆23Sep 25, 2026Updated 3 weeks ago
- Code for Zae Myung Kim's paper titled "Meta^n: Recursive Self-Improvement through Emergent Depth"☆36Aug 26, 2026Updated last month
- ☆12May 6, 2022Updated 4 years 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.
- ☆30Sep 21, 2026Updated last month
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 4 months ago
- Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups☆53Dec 23, 2024Updated last year
- ☆20Mar 17, 2025Updated last year
- Code for the paper Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation (CVPR 2023).☆34May 26, 2023Updated 3 years ago
- ☆43Aug 11, 2026Updated 2 months ago
- [ACL 2026] PIArena: A Platform for Prompt Injection Evaluation☆53Aug 31, 2026Updated last month
- open Source code for propensity evaluation☆21Apr 25, 2026Updated 5 months ago
- [NeurIPS'22] Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork. Haotao Wang, Junyuan Hong,…☆15Nov 27, 2023Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents☆59Jul 14, 2026Updated 3 months ago
- offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming☆18Jun 2, 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
- DeepSeek Harness 源码深度解析（20 章 + 总纲 + 全网调研）· 用 git-repo-deepresearch(含 ratify-loop/review-loop) 产出☆45Sep 1, 2026Updated last month
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆40Jul 31, 2026Updated 2 months ago
- The official code of On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment☆28May 13, 2026Updated 5 months ago
- [NeurIPS 2026] "Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory"☆20Sep 26, 2026Updated 3 weeks ago
- 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
- TRACE is an agentic jailbreaking framework that can reduce attack difficulty, induce the agent to execute end-to-end attack workflows thr…☆40Oct 1, 2026Updated 2 weeks ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Auditing AI agents: a curated list of papers, tools, datasets, benchmarks, and standards covering reliability, monitoring, failure attrib…☆155Updated this week
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆22May 6, 2025Updated last year
- [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments☆66Feb 9, 2026Updated 8 months ago
- Code for the paper "Searching Privacy Risks in Multi-Agent Systems via Simulation"☆25Oct 13, 2025Updated last year
- ☆25Jun 12, 2026Updated 4 months ago
- Code repository for the paper "Heuristic Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models"☆20Aug 7, 2025Updated last year
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆51Jun 1, 2026Updated 4 months ago
- A curated paper list for co-evolution in agentic systems☆52Aug 20, 2026Updated 2 months ago
- ☆24Dec 8, 2024Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆29May 14, 2025Updated last year
- PIForge: An Open Framework for RL-based Prompt Injection Red Teaming.☆36Sep 30, 2026Updated 3 weeks ago
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆25May 20, 2025Updated last year
- [NeurIPS 2022] "Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets" by Ruisi Cai*, Zhenyu Zh…☆21Oct 1, 2022Updated 4 years ago
- ☆95Jun 18, 2026Updated 4 months ago
- ☆17Nov 24, 2025Updated 10 months ago
- ☆17Jul 2, 2026Updated 3 months ago