The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
Paper • 2604.10577 • Published • 23
Valentin Lafargue
ValentinLAFARGUE
·
AI & ML interests
Bias, Fairness, Auditing.
Recent Activity
upvoted a paper about 16 hours ago
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents upvoted a paper about 16 hours ago
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and MitigationOrganizations
upvoted 2
papers about 16 hours ago
upvoted a paper 14 days ago
upvoted a paper 15 days ago
upvoted a paper 23 days ago
upvoted 3
papers 24 days ago
submitted a
paper to Daily Papers 24 days ago
authored 3
papers 25 days ago
Probing Cultural Signals in Large Language Models through Author Profiling
Paper • 2603.16749 • Published • 3
Exposing the Illusion of Fairness: Auditing Vulnerabilities to Distributional Manipulation Attacks
Paper • 2507.20708 • Published
Fairness is in the details: Face Dataset Auditing
Paper • 2504.08396 • Published
updated a
dataset 25 days ago
updated a
model 25 days ago
published a
dataset 27 days ago
published a
model 28 days ago
updated a
dataset 29 days ago
published a
dataset 29 days ago