ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
☆35Jul 10, 2026Updated last month
Alternatives and similar repositories for ATbench
Users that are interested in ATbench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A Diagnostic Guardrail Framework for AI Agent Safety and Security☆684Jun 8, 2026Updated 2 months ago
- Repo for paper "Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability"☆109Aug 15, 2026Updated last week
- Official Repo of Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents☆92Jun 2, 2026Updated 2 months ago
- 这倒是提醒我了☆407Jul 26, 2026Updated 3 weeks ago
- This repo is the official implementation of “Are Your Agents Upward Deceivers?”. The paper is accepted by ICML 2026.☆24Dec 15, 2025Updated 8 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆16May 2, 2026Updated 3 months ago
- All-in-One Safety Evaluation Framwork☆54Aug 12, 2026Updated last week
- ☆30Jun 13, 2026Updated 2 months ago
- 🧨 TradeTrap: Are LLM-based Trading Agents Truly Reliable and Faithful?☆82Nov 27, 2025Updated 8 months ago
- Diagnostic Framework for LLMs and MLLMs☆39Mar 2, 2026Updated 5 months ago
- ☆157Aug 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…☆34Jul 31, 2026Updated 3 weeks ago
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆30Jun 1, 2026Updated 2 months ago
- Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections☆22Jul 2, 2026Updated last month
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- [CVPR 2026] Code for Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory☆16Jul 30, 2026Updated 3 weeks ago
- [🏆ECCV'26] Official Repo for SlowBA: An efficiency backdoor attack towards VLM-based GUI agents☆18Jul 1, 2026Updated last month
- [CVPR Findings 2026] HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model☆17Mar 8, 2026Updated 5 months ago
- ☆44May 29, 2026Updated 2 months ago
- [CVPR'26] SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization☆22Feb 19, 2026Updated 6 months ago
- [AAAI 2026] Data and Code for Paper IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks☆50Nov 24, 2025Updated 9 months ago
- ☆24Dec 15, 2025Updated 8 months ago
- ☆25Apr 3, 2026Updated 4 months ago
- VLM2-Bench [ACL 2025 Main]: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues☆45May 20, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Official Repository of "Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Ste…☆28Mar 9, 2026Updated 5 months ago
- 本仓库整理公开披露的 OpenClaw 恶意 / 可疑 Skills 样本，并对其进行分类、分级与风险说明，供安全研究、平台治理和风险检测使用。☆20Mar 16, 2026Updated 5 months ago
- Code for "DynaGuard: A Dynamic Guardrail Model With User-Defined Policies."☆23Nov 3, 2025Updated 9 months ago
- [ICLR'26] Building a Foundational Guardrail for General Agentic Systems via Synthetic Data☆49Oct 26, 2025Updated 9 months ago
- [ACL 2026] PIArena: A Platform for Prompt Injection Evaluation☆47Apr 28, 2026Updated 3 months ago
- BrainWash: A Poisoning Attack to Forget in Continual Learning☆13Apr 15, 2024Updated 2 years ago
- [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆62Jul 21, 2025Updated last year
- ☆132Jul 29, 2026Updated 3 weeks ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆762Jun 2, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [NDSS 2026] Official repo for Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography☆60Mar 14, 2026Updated 5 months ago
- FreqDGT: Frequency-Adaptive Dynamic Graph Networks with Transformer for Cross-subject EEG Emotion Recognition☆15Jul 8, 2025Updated last year
- ☆43Mar 24, 2026Updated 5 months ago
- [EMNLP 2025] The code repo of paper "X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Com…☆40Nov 24, 2025Updated 9 months ago
- Official implementation of "TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards"☆32Jul 20, 2026Updated last month
- Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric☆16Nov 12, 2025Updated 9 months ago
- CyberGym-E2E is a large-scale benchmark built from real-world vulnerabilities in widely used open-source projects to evaluate AI agents' …☆54Jun 25, 2026Updated last month