Roberto Rigolin F. Lopes
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
FlowGuard introduces an identity-independent defense using flow matching to detect data-free model stealing attacks by identifying synthetic queries as out-of-distribution based on their lower-dimensional manifold structure.
This paper demonstrates that current AI model extraction defenses, which assume attacks come from single sources, are easily bypassed by coordinated, distributed threat actors.
Papers
FlowGuard: Flow Matching for Identity-Independent Detection of Data-Free Model Stealing Attacks on Energy System Intrusion Detection Systems
FlowGuard introduces an identity-independent defense using flow matching to detect data-free model stealing attacks by identifying synthetic queries as out-of-distribution based on their lower-dimensi…