Official Implementation for the paper "The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents"
☆15Apr 15, 2026Updated 6 months ago
Alternatives and similar repositories for OS_Blind
Users that are interested in OS_Blind are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official Implementation for the paper "Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base"☆26Sep 2, 2025Updated last year
- SHE: Trajectory-driven Safety Harness Evolution for LLM Agents☆21Aug 4, 2026Updated 2 months ago
- ☆18Mar 25, 2026Updated 6 months ago
- ☆39Jun 13, 2026Updated 4 months ago
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆16May 2, 2026Updated 5 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.
- [🏆ECCV'26] Official Repo for SlowBA: An efficiency backdoor attack towards VLM-based GUI agents☆20Oct 3, 2026Updated 3 weeks ago
- [ICML 2026 Spotlight] Official implementation of "PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipu…☆16Jun 16, 2026Updated 4 months ago
- ☆10May 23, 2025Updated last year
- CoAct-1: Computer-using Agents with Coding as Actions☆29Jun 2, 2026Updated 4 months ago
- Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups☆53Dec 23, 2024Updated last year
- offical implementation of MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming☆18Jun 2, 2025Updated last year
- [CVPR'26] SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization☆23Feb 19, 2026Updated 8 months ago
- Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections☆23Jul 2, 2026Updated 3 months ago
- ☆26Dec 18, 2025Updated 10 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.
- [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments☆66Feb 9, 2026Updated 8 months ago
- OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]☆78Sep 18, 2025Updated last year
- PIForge: An Open Framework for RL-based Prompt Injection Red Teaming.☆36Sep 30, 2026Updated 3 weeks ago
- Artifacts for SoK: Can Trajectory Generation Combine Privacy and Utility?☆15Jun 27, 2024Updated 2 years ago
- Official implementation of "TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards"☆33Sep 29, 2026Updated 3 weeks ago
- One-sided verification under limited expert review: audited review of solutions and papers (mathematics for now).☆30Updated this week
- [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
- A Benchmark for Evaluating Safety and Trustworthiness in Web Agents for Enterprise Scenarios☆30Mar 12, 2026Updated 7 months ago
- Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Self-Improving Personal Agents☆17Oct 10, 2026Updated 2 weeks 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.
- NLPBench: Evaluating NLP-Related Problem-solving Ability in Large Language Models☆10Oct 27, 2023Updated 2 years ago
- Evaluation Code@CoVEBench. Dual-level metrics.☆19Jul 4, 2026Updated 3 months ago
- ArterialNet reconstructs arterial blood pressure (ABP) waveform☆15Feb 24, 2025Updated last year
- ☆47Updated this week
- PyTorch implementation of "A Simple Baseline for Low-Budget Active Learning".☆14Dec 22, 2021Updated 4 years ago
- Learning from Indirect Observations☆11Jul 16, 2021Updated 5 years ago
- AHA is autoresearch for agent safety: one agent red-teams a production agent overnight and comes back with reusable explanations of why t…☆35Sep 26, 2026Updated 3 weeks ago
- ☆19Mar 9, 2026Updated 7 months ago
- ☆26May 28, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- A framework for testing and evaluating AI agents across various task domains, designed for misalignment interpretability research.☆33Sep 17, 2026Updated last month
- Unofficial Pytorch implementation of the paper 'Categorical Reparameterization with Gumbel-Softmax' and 'The Concrete Distribution: A Con…☆11Apr 27, 2021Updated 5 years ago
- The code for our work☆18Apr 7, 2024Updated 2 years ago
- https://arxiv.org/abs/2404.10917☆14Mar 18, 2025Updated last year
- VERA: Scaling Verifiable Environments for Agentic co-Evolution — model-harness co-evolution for long-horizon agents☆16Oct 6, 2026Updated 2 weeks ago
- Rui Qian, Chuanhang Deng, Qiang Huang, et al.: AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation (ACL 2026)☆18Aug 12, 2026Updated 2 months ago
- A curated list of LLM/MLLM guardrails, safety benchmarks, guard models, jailbreak attacks, moderation datasets, and evaluation tools.☆38Oct 7, 2026Updated 2 weeks ago