4 papers
KSAFE-MM: A Multimodal Safety Benchmark via Localized Contextualization for Korean Cultural Risks
Yongwoo Kim, Sojung An, Yunjin Park +8
Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and vision. Current MLLM safety evaluat…
Erase at the Core: Representation Unlearning for Machine Unlearning
Jaewon Lee, Yongwoo Kim, Donghyun Kim
Many approximate machine unlearning methods demonstrate strong logit-level forgetting -- such as near-zero accuracy on the forget set -- yet continue to preserve substantial inform…
Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-weighted Adaptation
Yongwoo Kim, Sungmin Cha, Hyunsoo Kim +2
With the increasing versatility of text-to-image diffusion models, the ability to selectively erase undesirable concepts (e.g., harmful content) has become indispensable. However,…
Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols
Yongwoo Kim, Sungmin Cha, Donghyun Kim
Machine unlearning is a process to remove specific data points from a trained model while maintaining the performance on the retain data, addressing privacy or legal requirements.…