Author

Woohyuk Choi

h-index 4 View on Semantic Scholar

We have 2 of 9 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Jul 2026

DualView: Preventing Indirect Prompt Injection in Personal AI Agents

DualView deterministically prevents instructions in untrusted data from directly steering the agent's tool calls from directly steering the agent's tool calls; this guarantee does not depend on recognizing the evaluated attack templates.

Juhee Kim, Woohyuk Choi, Taehyun Kang et al. · arXiv.org · 1 citation

Jul 2026

Agent Data Injection Attacks are Realistic Threats to AI Agents

A new category of IPI, agent data injection attacks (ADI), which exposes a critical gap in agent security, signifying that current AI agents do not employ a fundamental security principle: current agents do not isolate trusted data from untrusted data.

Woohyuk Choi, Juhee Kim, Taehyun Kang et al. · arXiv.org · 3 citations