OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]
☆69Sep 18, 2025Updated 10 months ago
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:
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆33Jan 23, 2025Updated last year
- [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments☆57Feb 9, 2026Updated 5 months ago
- A powerful white-box adversarial attack that exploits knowledge about the geometry of neural networks to find minimal adversarial perturb…☆12Aug 5, 2020Updated 5 years ago
- ☆40Nov 7, 2025Updated 8 months ago
- ☆17Mar 16, 2026Updated 4 months 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.
- ☆13Jun 23, 2022Updated 4 years ago
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆210Updated this week
- The open-source AISI toolkit for sandboxing agentic evaluations☆25Aug 7, 2025Updated 11 months ago
- ☆47Dec 9, 2025Updated 7 months 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 10 months ago
- AI Control evaluation library. Built natively on Inspect AI.☆17Feb 25, 2026Updated 4 months ago
- [WACV 2026] MomentMix Augmentation with Length-Aware DETR for Temporally Robust Moment Retrieval☆14Sep 18, 2025Updated 10 months ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆44Sep 11, 2023Updated 2 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆15Dec 7, 2021Updated 4 years ago
- [ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.☆25Jul 25, 2024Updated last year
- ☆149Aug 11, 2025Updated 11 months ago
- [ICLR 2025] DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models☆19Mar 25, 2025Updated last year
- Code for the API, workload execution, and agents underlying the LLMail-Inject Adpative Prompt Injection Challenge☆25Apr 9, 2026Updated 3 months ago
- Run Inspect AI evals in the cloud☆32Updated this week
- Codebase to fully reproduce the results of "No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO" (M…☆33Nov 20, 2024Updated last year
- [USENIX'23] TPatch: A Triggered Physical Adversarial Patch☆25Aug 8, 2023Updated 2 years ago
- [NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents☆85Apr 24, 2026Updated 2 months ago
- 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.
- ☆19Feb 25, 2024Updated 2 years ago
- ☆25May 25, 2024Updated 2 years ago
- ☆13Nov 12, 2024Updated last year
- A School for All Seasons on Trustworthy Machine Learning☆12Jun 30, 2021Updated 5 years ago
- CoAct-1: Computer-using Agents with Coding as Actions☆27Jun 2, 2026Updated last month
- Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".☆56Jan 18, 2022Updated 4 years ago
- Causal Analysis of Agent Behavior for AI Safety☆21Jun 27, 2023Updated 3 years ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆670Jun 2, 2026Updated last month
- Understanding and Improving Fast Adversarial Training [NeurIPS 2020]☆96Sep 23, 2021Updated 4 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- This is the repository for paper EscapeBench: Pushing Language Models to Think Outside the Box☆18Dec 19, 2024Updated last year
- ☆50Mar 2, 2024Updated 2 years ago
- [ACL 2024] Code for the paper "ALaRM: Align Language Models via Hierarchical Rewards Modeling"☆25Mar 28, 2024Updated 2 years ago
- Source code for "Neural Anisotropy Directions"☆16Nov 17, 2020Updated 5 years ago
- Sharpness-Aware Minimization Leads to Low-Rank Features [NeurIPS 2023]☆29Sep 22, 2023Updated 2 years ago
- ☆14Jul 25, 2025Updated 11 months ago
- Source code of "Hold me tight! Influence of discriminative features on deep network boundaries"☆21Dec 10, 2021Updated 4 years ago