Skip to content
conftrace_

safety threat

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

feedback (1) adversarial cases (1) computer-using agent (1) security threat (1) large language model (1) multimodal input (1) red teaming (1) vision-language model (1) in-context learning (1)

Papers

JARVIS or Ultron? A Survey on the Safety and Security Threats of Computer-Using Agents ACL 2026 TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models ICML 2025