OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]
☆78Sep 18, 2025Updated last year
Alternatives and similar repositories for os-harm
Users that are interested in os-harm 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 "The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Co…☆15Apr 15, 2026Updated 6 months ago
- [NeurIPS 2025] Official repository of RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents☆125Dec 2, 2025Updated 10 months ago
- [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments☆66Feb 9, 2026Updated 8 months ago
- ☆49Dec 9, 2025Updated 10 months ago
- ☆46Jun 19, 2025Updated last year
- 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.
- Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups☆53Dec 23, 2024Updated last year
- ☆15Jan 30, 2026Updated 9 months ago
- Official Code implementation of "Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators"☆11Sep 19, 2025Updated last year
- ☆13Jun 23, 2022Updated 4 years ago
- On the effectiveness of adversarial training against common corruptions [UAI 2022]☆30May 16, 2022Updated 4 years ago
- ☆45Nov 7, 2025Updated 11 months ago
- Implementation of average- and worst-case robust flatness measures for adversarial training.☆15Nov 5, 2021Updated 4 years ago
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆258Oct 22, 2026Updated last week
- An O-RAN compliant xApp employing deep learning to detect 5G cellular network threats and anomalies☆12Aug 6, 2025Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆99Updated this week
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆146Feb 19, 2025Updated last year
- ☆166Aug 11, 2025Updated last year
- ☆201Oct 31, 2025Updated 11 months ago
- [NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments☆3,241Updated this week
- A simple, modular, non-brittle framework for implementing text-based Reflexion agents.☆10Sep 1, 2023Updated 3 years ago
- Provable Robustness of ReLU networks via Maximization of Linear Regions [AISTATS 2019]☆31Jul 15, 2020Updated 6 years ago
- Consuming Resrouce via Auto-generation for LLM-DoS Attack under Black-box Settings☆25Sep 1, 2025Updated last year
- FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens☆19Sep 8, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- [ACL 2026] PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation☆14Jun 12, 2026Updated 4 months ago
- ☆43May 21, 2025Updated last year
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]☆21May 2, 2024Updated 2 years ago
- A framework for the science of agents and agents for science☆21Updated this week
- [ECCV 2024] Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models☆21Jul 17, 2024Updated 2 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆46Sep 11, 2023Updated 3 years ago
- ☆18May 7, 2025Updated last year
- Provable Worst Case Guarantees for the Detection of Out-of-Distribution Data☆13Sep 20, 2022Updated 4 years ago
- INC: Implicit Neural Correction for PDE Solvers☆14Oct 2, 2026Updated 3 weeks 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.
- [ACL 2026] PIArena: A Platform for Prompt Injection Evaluation☆55Aug 31, 2026Updated last month
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆51Jun 1, 2026Updated 4 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆399Jan 23, 2025Updated last year
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆97Sep 1, 2025Updated last year
- Official implementation of the WASP web agent security benchmark☆97Apr 13, 2026Updated 6 months ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆964Jun 2, 2026Updated 4 months ago
- Code for the API, workload execution, and agents underlying the LLMail-Inject Adpative Prompt Injection Challenge☆27Oct 20, 2026Updated last week