The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
Paper • 2604.10577 • Published • 24
Hanson Tang
HansonTang
·
AI & ML interests
None yet
Recent Activity
updated a model 12 months ago
HansonTang/distilbert-base-uncased-finetuned-cola published a model 12 months ago
HansonTang/distilbert-base-uncased-finetuned-colaOrganizations
None yet
upvoted a paper 3 days ago