| Date | Main | Opponent | Title |
|---|
| 26.7.21 | Chaejin Lim | Seonhye Park | Big Help or Big Brother? Auditing Tracking, Profiling, and Personalization in Generative AI Assistants |
| 26.7.28 | Woojin Jeon | Taeyoung Kim | ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior |
| 26.8.4 | Yena Cho | Heejun Jang | DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation |
| 26.8.11 | Sangjun Chae | Seungwoo Yoo | SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models |
| 26.8.18 | Jieun Hwang | Woojin Jeon | Fingerprint Fragment Expansion using Image Outpainting Approach based on Spectral Normalization PatchGAN |
| 26.8.25 | Kyungbin Ryu | Taeyoung Kim | CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor |
| 26.9.1 | Seungwoo Yoo | Sangjun Chae | MPMA: Preference Manipulation Attack Against Model Context Protocol |
| 26.9.8 | Jungho Oh | Joonhyung Park | Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems |
| 26.9.15 | Seungho Kim | Kyungbin Ryu | Zero2Text: Zero-Training Cross-Domain Inversion Attacks on Textual Embeddings |
| 26.9.22 | Heesung Jeong | - | MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents |
| 26.9.29 | Sun Ki Kim | - | |
| 26.10.6 | Maharani Intan | - | |
| 26.10.13 | Woojin Jeon | - | |
| 26.10.20 | Seojin Park | - | |
| 26.10.27 | Chaejin Lim | - | |
| 26.11.3 | Kyungbin Ryu | - | |
| 26.11.10 | Heejun Jang | - | |
| 26.11.17 | Yena Cho | - | |
| 26.11.24 | Byungchan Choi | - | |
| 26.12.1 | Daeun Song | - | |
| 26.12.8 | Joonhyung Park | - | |
| 26.12.15 | Sangjun Chae | - | |
| 26.12.22 | Jieun Hwang | - | |
| 26.12.29 | Subin Cho | - | |
| 27.1.5 | Taeyoung Kim | - | |