The Official Implementation of "SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment"
☆22Sep 2, 2026Updated 2 months ago
Alternatives and similar repositories for SafeEvolve
Users that are interested in SafeEvolve are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- SHE: Trajectory-driven Safety Harness Evolution for LLM Agents☆24Aug 4, 2026Updated 3 months ago
- The public repository of ICML 2026 "SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM …☆15May 6, 2026Updated 6 months ago
- SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing☆15Sep 23, 2026Updated last month
- [COLM 2026] Official implementation for "GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning"☆15Mar 4, 2026Updated 8 months ago
- ☆40Jun 13, 2026Updated 5 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Code for ICCV2025 paper——IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves☆18Jul 11, 2025Updated last year
- Official implementation of "SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment"☆14Jun 2, 2026Updated 5 months ago
- offical implementation of Jailbreak-R1☆17Jul 16, 2025Updated last year
- ☆33May 14, 2026Updated 5 months ago
- Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency☆16Aug 6, 2025Updated last year
- CoEvo-RSI: model-harness co-evolution for LLM agents☆18Oct 20, 2026Updated 3 weeks ago
- AHA is autoresearch for agent safety: one agent red-teams a production agent overnight and comes back with reusable explanations of why t…☆38Sep 26, 2026Updated last month
- ☆70May 21, 2025Updated last year
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆62Jul 16, 2026Updated 3 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.
- ☆17Jul 2, 2026Updated 4 months ago
- An Adversarial Co-Evolution Framework for LLM Agent Safety☆35Oct 16, 2026Updated 3 weeks ago
- A reader-centered, write-first Codex skill for planning, drafting, revising, and auditing academic papers.☆19Jul 23, 2026Updated 3 months ago
- 中国人民大学 YOJ 题库☆16Jun 9, 2022Updated 4 years ago
- 🦾 SeClaw: The Security Armored Personal AI Assistant☆31Aug 27, 2026Updated 2 months ago
- Self-HPO: self-improving harness + policy co-optimization for agentic SWE☆65Oct 19, 2026Updated 3 weeks ago
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 5 months ago
- A nano re-implementation of Cordis and DeepSeek Harness, an AI agent runtime built out of plugins, small enough to read in an afternoon.☆15Aug 18, 2026Updated 2 months ago
- [NeurIPS 2024] UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation☆10Jul 5, 2025Updated last year
- 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.
- 用强化学习来玩微信跳一跳☆10Jul 10, 2022Updated 4 years ago
- ☆11Nov 29, 2023Updated 2 years ago
- Implemention of "Robust Watermarking of Neural Network with Exponential Weighting" in TensorFlow.☆13Dec 2, 2020Updated 5 years ago
- ☆22Mar 28, 2026Updated 7 months ago
- Official implementation of Visco-Attack (EMNLP 2025 Main). An open-source one-click reproduction script is also provided.☆31Apr 11, 2026Updated 7 months ago
- Code for the paper Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation (CVPR 2023).☆34May 26, 2023Updated 3 years ago
- Code for accepted paper at ICLR 2026☆17Oct 15, 2026Updated 3 weeks ago
- Data and code for the paper: Finding Safety Neurons in Large Language Models☆31Jan 29, 2026Updated 9 months ago
- 中文金融数据集☆13Nov 3, 2022Updated 4 years 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.
- A Diagnostic Guardrail Framework for AI Agent Safety and Security☆708Jun 8, 2026Updated 5 months ago
- BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically i…☆51Mar 16, 2026Updated 7 months ago
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆40Jul 31, 2026Updated 3 months ago
- 包含USTC自动化专业大一到大三相关资料，后续随缘更新☆39Jul 1, 2026Updated 4 months ago
- ☆13Feb 11, 2026Updated 9 months ago
- [NeurIPS 2026] The official implementation of our NeurIPS 2026 paper "When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-…☆14Sep 25, 2026Updated last month
- Official implementation for "DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling" (IEEE S&P 2026)☆14Jan 28, 2026Updated 9 months ago
Are these results useful?