Securing Federated Learning: A Covert Communication-Based Approach

Xie, Yuan-ai; Kang, Jiawen; Niyato, Dusit; Van, Nguyen Thị Thanh; Luong, Nguyen Cong; Liu, Zhixin; Yu, Han

doi:10.1109/mnet.117.2200065

Cited by 12 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve the non-convex problem, we adopt a Successive Convex Approximation (SCA) algorithm. We would like to highlight that our work is significantly different from the previous work [6]. First, the work [6] only considers a single FJ, while our work considers multiple FJs that better support the mobile devices.…”

Section: Introductionmentioning

confidence: 94%

“…We would like to highlight that our work is significantly different from the previous work [6]. First, the work [6] only considers a single FJ, while our work considers multiple FJs that better support the mobile devices. Second, the work [6] does not consider the low jamming cost and the truthfulness of the FJs, while our work does.…”

Section: Introductionmentioning

confidence: 94%

“…The truthful auction guarantees the truthfulness and allows the BS to select the best FJ with the lowest cost. Furthermore, we consider the budget of the BS, which is also investigated in [6]. Specifically, we investigate a secure FL system.…”

Section: Introductionmentioning

confidence: 99%

“…First, the work [6] only considers a single FJ, while our work considers multiple FJs that better support the mobile devices. Second, the work [6] does not consider the low jamming cost and the truthfulness of the FJs, while our work does. Third, the work [6] does not introduce the auction mechanism, while our work does.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Joint Power Cost and Latency Minimization for Secure Collaborative Learning System

Van

Quang

Luong

2022

JCC

View full text Add to dashboard Cite

This work investigates the model update security in a collaborative learning or federated learning network by using the covert communication. The CC uses the jamming signal and multiple friendly jammers (FJs) are deployed that can offer jamming services to the model owner, i.e., a base station (BS). To enable the BS to select the best FJ, i.e., the lowest cost FJ, a truthful auction is adopted. Then, a problem is formulated to optimize the jamming power, transmission power, and local accuracy. The objective is to minimize the training latency, subject to the security performance requirement and budget of the BS. To solve the non-convex problem, we adopt a Successive Convex Approximation algorithm. The simulation results reveals some interesting things. For example, the trustful auction reduces the jamming cost of the BS as the number of FJs increases.

show abstract

Section: Introductionmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Joint Power Cost and Latency Minimization for Secure Collaborative Learning System

Van

Quang

Luong

2022

JCC

View full text Add to dashboard Cite

show abstract

“…The conventional cryptography approaches [2] usually focus on protecting the transmission content or increasing message decoding complexity, while the physical-layer security [3], [4] approaches exploit the intrinsic wireless fading channels properties to minimize the information leakage to the eavesdroppers. In fact, a higher level of security is to hide the existence of the communication, which not only can be applied in all aforementioned application scenarios [5]- [8], but also meets more critical demands from military or security agencies. To address this high level security, covert communications [9], [10], which shields the existence of message transmissions against the detection of a warden, are emerging as a cutting-edge wireless communication security technique, and have recently attracted significant research attention.…”

Section: Introductionmentioning

confidence: 99%

Optimal Probabilistic Constellation Shaping for Covert Communications

Haihong

et al. 2022

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

In this paper, we investigate the optimal probabilistic constellation shaping design for covert communication systems from a practical view. Different from conventional covert communications with equiprobable constellations modulation, we propose non-equiprobable constellations modulation schemes to further enhance the covert rate. Specifically, we derive covert rate expressions for practical discrete constellation inputs for the first time. Then, we study the covert rate maximization problem by jointly optimizing the constellation distribution and power allocation. In particular, an approximate gradient descent method is proposed for obtaining the optimal probabilistic constellation shaping. To strike a balance between the computational complexity and the transmission performance, we further develop a framework that maximizes a lower bound on the achievable rate where the optimal probabilistic constellation shaping problem can be solved efficiently using the Frank-Wolfe method. Extensive numerical results show that the optimized probabilistic constellation shaping strategies provide significant gains in the achievable covert rate over the state-of-the-art schemes.

show abstract