Don't Trust the AI Ecosystem: Analyzing Privacy Leakage in Compromised Open-Source Components

본문 미리보기

arXiv:2607.27886v1 Announce Type: new Abstract: Existing model inversion (MI) attacks predominantly rely on post-training optimization to recover private data from model outputs. However, these methods are fundamentally constrained by the target model's generalization bottleneck, often yielding generic features rather than specific identities, particularly on high-dimensional datasets. In this paper, we introduce GradLock, a novel training-time injection attack that stealthily injects sensitive