[ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
☆57Feb 9, 2026Updated 5 months ago
Alternatives and similar repositories for RedTeamCUA
Users that are interested in RedTeamCUA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆23Jan 30, 2026Updated 5 months ago
- Official implementation of the WASP web agent security benchmark☆98Apr 13, 2026Updated 3 months ago
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆15May 2, 2026Updated 2 months ago
- [ICLR 2025] Dissecting adversarial robustness of multimodal language model agents☆140Feb 19, 2025Updated last year
- ☆192Oct 31, 2025Updated 8 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.
- [EMNLP 2024 Tutorial] Language Agents: Foundations, Prospects, and Risks☆10Nov 27, 2024Updated last year
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆29Jul 6, 2026Updated 2 weeks ago
- Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups☆51Dec 23, 2024Updated last year
- Web Verbs is an extension to NLWeb from Microsoft Research☆15May 5, 2026Updated 2 months ago
- [ASPLOS 2026, Best Paper Honorable Mention] Highly Automated Verification of Security Properties for Unmodified System Software☆19Mar 31, 2026Updated 3 months ago
- [CVPR'26] SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization☆21Feb 19, 2026Updated 5 months ago
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆27Jun 1, 2026Updated last month
- An Autonomous Curriculum Reinforcement Learning framework that steers agents to continually learn in specific environments with zero huma…☆38Jun 7, 2026Updated last month
- [NDSS 2026] Official repo for Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography☆59Mar 14, 2026Updated 4 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.
- Mobile GUI Agents under Real-world Threats: Are We There Yet?☆17May 18, 2026Updated 2 months ago
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆20Mar 22, 2026Updated 4 months ago
- PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization☆18Dec 10, 2025Updated 7 months ago
- MutliAgent Attack☆15Oct 3, 2024Updated last year
- A benchmark and generation framework for malicious agent skills.☆40Jun 10, 2026Updated last month
- Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments (EMNLP'2024)☆37Dec 29, 2024Updated last year
- True Few-Shot BioIE: Benchmarking GPT-3 In-Context and Small PLM Fine-Tuning☆12Jul 6, 2022Updated 4 years ago
- ☆15May 13, 2026Updated 2 months ago
- The implementation for paper "UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in …☆17Jul 3, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections☆21Jul 2, 2026Updated 3 weeks ago
- ☆25May 28, 2025Updated last year
- ☆25Apr 3, 2025Updated last year
- ☆23Jun 18, 2025Updated last year
- OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]☆69Sep 18, 2025Updated 10 months ago
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆467Oct 29, 2025Updated 8 months ago
- [TMLR 2025] Official implementation of AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation☆27Jun 17, 2025Updated last year
- ☆57May 9, 2025Updated last year
- [EMNLP'25] AutoSDT is a fully automatic pipeline to collect data-driven scientific coding tasks to train co-scientist models.☆21Aug 11, 2025Updated 11 months ago
- 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.
- An Illusion of Progress? Assessing the Current State of Web Agents☆192Jun 25, 2026Updated last month
- [ACL'23 Findings] "Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors"☆39Dec 22, 2023Updated 2 years ago
- MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following☆16Oct 31, 2024Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆684Jun 2, 2026Updated last month
- PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses☆22Jul 17, 2026Updated last week
- [ICML'26] "Agent Learning via Early Experience" (Open-source reproduction)☆136Jul 8, 2026Updated 2 weeks ago
- Implementation of "Beyond Classification: Inferring Function Names in Stripped Binaries via Domain Adapted LLMs" (NDSS'25)☆47Jun 5, 2025Updated last year