Author

YoungMi Kim

1 paper indexed here

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