2 papers
cs.CR2026
Don't Trust the AI Ecosystem: Analyzing Privacy Leakage in Compromised Open-Source Components
Jin-Seong Kim, Han-Ju Lee, Seok-Won Hong +4
Existing model inversion (MI) attacks predominantly rely on post-training optimization to recover private data from model outputs. However, these methods are fundamentally constrai…
cs.CV2025
DPAC: Distribution-Preserving Adversarial Control for Diffusion Sampling
Han-Jin Lee, Han-Ju Lee, Jin-Seong Kim +1
Adversarially guided diffusion sampling often achieves the target class, but sample quality degrades as deviations between the adversarially controlled and nominal trajectories acc…