Hyo Seo Kim — accepted AI-conference papers

2026

MoCo-EA: Exploiting Adversarial Mode Connectivity for Efficient Evolutionary Attacks

Hyo Seo Kim, Gang Luo, Can Chen, Binghui Wang, Yue Duan, Ren Wang

ICML 2026poster

Evolutionary algorithms for adversarial attacks leverage population-based search to discover perturbations without gradient information, but suffer from inefficient crossover operations that destroy adversarial properties through discrete interpolation. We introduce Mode Connectivity Evolutionary At…

Cited by 0 Source ↗Scholar ↗

2025

NegMerge: Sign-Consensual Weight Merging for Machine Unlearning

Hyo Seo Kim, Dongyoon Han, Junsuk Choe

ICML 2025poster

Machine unlearning aims to selectively remove specific knowledge from a trained model. Existing approaches, such as Task Arithmetic, fine-tune the model on the forget set to create a task vector (i.e., a direction in weight space) for subtraction from the original model's weight. However, their effe…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗