DECIFR: Domain-Aware Exfiltration of Circuit Information from Federated Gradient Reconstruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915948440584192 |
|---|---|
| author | Lee, Gijung Bowman, Wavid Dizon-Paradis, Olivia P. Dizon-Paradis, Reiner N. Wilson, Ronald Woodard, Damon L. Forte, Domenic |
| author_facet | Lee, Gijung Bowman, Wavid Dizon-Paradis, Olivia P. Dizon-Paradis, Reiner N. Wilson, Ronald Woodard, Damon L. Forte, Domenic |
| contents | Federated Learning (FL) is a promising approach for multiparty collaboration as a privacy-preserving technique in hardware assurance, but its security against adversaries with domain-specific knowledge is underexplored. This paper demonstrates a critical vulnerability where available standard cell library layouts (SCLL) can be exploited to compromise the privacy of sensitive integrated circuit (IC) training data. We introduce DECIFR, a novel two-stage Membership Inference Attack (MIA) that requires no auxiliary dataset. The attack employs a guided Gradient Inversion Attack (GIA) to reconstruct a client's training images from intercepted model updates. Our findings reveal that the fidelity of these reconstructions directly correlates with membership status, allowing an adversary to reliably distinguish members from non-members based on image quality. This work exposes a practical threat that overcomes the limitations of conventional attacks and underscores that standard FL protocols are insufficient for securing domains with extensive knowledge. We conclude that robust defenses are essential for the secure application of FL in hardware assurance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19915 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DECIFR: Domain-Aware Exfiltration of Circuit Information from Federated Gradient Reconstruction Lee, Gijung Bowman, Wavid Dizon-Paradis, Olivia P. Dizon-Paradis, Reiner N. Wilson, Ronald Woodard, Damon L. Forte, Domenic Cryptography and Security Federated Learning (FL) is a promising approach for multiparty collaboration as a privacy-preserving technique in hardware assurance, but its security against adversaries with domain-specific knowledge is underexplored. This paper demonstrates a critical vulnerability where available standard cell library layouts (SCLL) can be exploited to compromise the privacy of sensitive integrated circuit (IC) training data. We introduce DECIFR, a novel two-stage Membership Inference Attack (MIA) that requires no auxiliary dataset. The attack employs a guided Gradient Inversion Attack (GIA) to reconstruct a client's training images from intercepted model updates. Our findings reveal that the fidelity of these reconstructions directly correlates with membership status, allowing an adversary to reliably distinguish members from non-members based on image quality. This work exposes a practical threat that overcomes the limitations of conventional attacks and underscores that standard FL protocols are insufficient for securing domains with extensive knowledge. We conclude that robust defenses are essential for the secure application of FL in hardware assurance. |
| title | DECIFR: Domain-Aware Exfiltration of Circuit Information from Federated Gradient Reconstruction |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2604.19915 |