Domenic Forte

The paper proposes 'mimetic deception,' a novel IP camouflaging technique that structurally disguises a functional IP as a different appearance IP, thereby thwarting both structural reverse engineering and side-channel attacks like DPA.

This paper investigates the use of Federated Learning (FL) for hardware assurance, demonstrating that while FL improves model performance over centralized learning, it remains vulnerable to gradient inversion attacks that can expose proprietary intellectual property.

The paper introduces DECIFR, a novel two-stage Membership Inference Attack (MIA) that exploits standard cell library layouts to reconstruct sensitive IC training data from intercepted federated model updates, demonstrating a critical privacy vulnerability in standard Federated Learning.

This paper presents a novel data-free Membership Inference Attack (MIA) that uses gradient inversion on Standard Cell Library Layouts (SCLLs) to reconstruct sensitive hardware images from intercepted Federated Learning model updates, demonstrating significant IP leakage.