EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

Adversarial Latency Watermarking: Covertly Encoding Zero Bit Keys in Federated Learning Model Updates

Barakat Saad Ibrahim, Ahmed Hameed Shakir, Hasan Jameel

Al-Noor Journal of Engineering Management and Computer Science · 15.08.2026 · 202-213

DOI: 10.71229/v37bk664 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Al-Noor Journal of Engineering Management and Computer Science, online erschienen am 15.08.2026. Verfasst von Barakat Saad Ibrahim und 2 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) protects client data by sharing only model updates, yet current defences ignore timing metadata. We show that a single malicious client can embed a 128 bit cryptographic key into the final global model by modulating update latency alone, bypassing gradient-value inspections, differential privacy (DP), and secure aggregation (SecAgg). We model the latency-to-weight channel as an additive white Gaussian noise (AWGN) process with CPU jitter and derive its information-theoretic capacity, demonstrating that 134 rounds suffice to transmit 128 bits at ε=500 μs. We design Jitter Deconv, a spread-spectrum encoder/decoder that maps Gold-code delays to weight-space imprints and recovers keys with bit-error rate (BER) 1.02×10⁻³ under DP-SGD (σ=10⁻²) and SecAgg. To detect the covert channel, we introduce Latency Print, a lightweight autocovariance-based statistic achieving AUC=0.98 and ≤0.7 % false-positive rate with

Zitieren

APA

Ibrahim, B. S., Shakir, A. H., & Jameel, H. (2026). Adversarial Latency Watermarking: Covertly Encoding Zero Bit Keys in Federated Learning Model Updates. Al-Noor Journal of Engineering Management and Computer Science, 202-213. https://doi.org/10.71229/v37bk664

Vancouver

Ibrahim BS, Shakir AH, Jameel H. Adversarial Latency Watermarking: Covertly Encoding Zero Bit Keys in Federated Learning Model Updates. Al-Noor Journal of Engineering Management and Computer Science. 2026:202-213. doi:10.71229/v37bk664

BibTeX
@article{Ibrahim2026,
  author = {Ibrahim, Barakat Saad and Shakir, Ahmed Hameed and Jameel, Hasan},
  title = {Adversarial Latency Watermarking: Covertly Encoding Zero Bit Keys in Federated Learning Model Updates},
  journal = {Al-Noor Journal of Engineering Management and Computer Science},
  year = {2026},
  pages = {202--213},
  doi = {10.71229/v37bk664}
}
Kostenlos starten →