From the 1 of 2 linked papers with an AI index.
2 papers
cs.CL2026
HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human-LLM Collaborative Writing
Euntae Kim, Soomin Han, Buru Chang
The paper introduces HarDBench, a benchmark that evaluates how vulnerable large language models are to jailbreak attacks when used as co-authors in draft-based writing, and propose…
cs.CV2026
Making Implicit Preservation Intent Explicit in Conversational Image Editing
Soomin Han, Jihyung Ahn, Bumsoo Kim +1
Conversational image editing requires preserving not only visible content, but also content that temporarily disappears across turns. When newly added or modified content occludes…