Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching
Model Inversion Attacks (MIAs) aim to reconstruct representative training samples of target identities from face recognition models, exposing critical security vulnerabilities. Existing methods typically rely on indirect guidance or highly stochastic guidance, making it difficult to stably optimize generation trajectories toward target facial images. In this paper, we propose Steering Flow Model Inversion (SFMI), a novel two-stage white-box model inversion method that reformulates inversion as a trajectory-steering task. Specifically, Step I, Learning a Generic Flow Matching Prior, pre-trains
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar name plus overlapping authors · 67%bytedance/deer-flow →
“Title similarity 0.73; shared authors: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%google-research/google-research →
“Shared author/contributor keys: sun”
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- LinkedLinked via arxiv author · 85%Ye Lu →
“Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching”
- LinkedLinked via arxiv author · 85%Shen Wang →
“Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching”
- LinkedLinked via arxiv author · 85%Zhaoyang Zhang →
“Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching”
- LinkedLinked via arxiv author · 85%Yihan Yan →
“Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching”