Differentially Private Distributed Optimization
Open accessThe DOI matches its Crossref record; 16 of the 17 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
In distributed optimization and iterative consensus literature, a standard problem is for N agents to minimize a function f over a subset of Euclidean space, where the cost function is expressed as a sum Σ fi. In this paper, we study the private distributed optimization problem (PDOP) with the additional requirement that the cost function of the individual agents should remain differentially private. The adversary attempts to infer information about the private cost functions from the messages that the agents exchange. Achieving differential privacy requires that any change of an individual's cost function only results in unsubstantial changes in the statistics of the messages. We propose a class of iterative algorithms for solving PDOP, which achieves differential privacy and convergence to a common value. Our analysis reveals the dependence of the achieved accuracy and the privacy levels on the the parameters of the algorithm. We observe that to achieve ϵ-differential privacy the accuracy of the algorithm has the order of O(1/ϵ2).
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“current work on the hybrid model typically assumes that regardless of the user trust preference, their data comes from the same distribution [40, 39, 57].”
From Advances and Open Problems in Federated Learning (2021) · cites this paper as [57]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Consensus and Cooperation in Networked Multi-Agent Systems
Olfati-Saber, R., Fax, J. A., & Murray, R. M. (2007) · Proceedings of the IEEE · doi:10.1109/jproc.2006.887293 · Cited by 10,522 · cited 1×
“For instance, such algorithms have been designed for the smart grids [3] and sensor networks [13].”
MethodDwork, C. (2006) · Lecture Notes in Computer Science · doi:10.1007/11787006_1 · Cited by 5,291 · cited 1×
“Categories and Subject Descriptors D.1.3 [Software]: Concurrent Programming—Distributed programming General Terms Algorithm Keywords Distributed Optimization, Differential Privacy, Iterative Consensus”
BackgroundInfluentialDistributed Subgradient Methods for Multi-Agent Optimization
Nedic, A., & Ozdaglar, A. (2009) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2008.2009515 · Cited by 3,719 · cited 2×
“Categories and Subject Descriptors D.1.3 [Software]: Concurrent Programming—Distributed programming General Terms Algorithm Keywords Distributed Optimization, Differential Privacy, Iterative Consensus”
BackgroundInfluentialDifferential Privacy: A Survey of Results
Dwork, C. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-79228-4_1 · Cited by 3,542 · cited 1×
“Categories and Subject Descriptors D.1.3 [Software]: Concurrent Programming—Distributed programming General Terms Algorithm Keywords Distributed Optimization, Differential Privacy, Iterative Consensus”
BackgroundInfluentialDistributed asynchronous deterministic and stochastic gradient optimization algorithms
Tsitsiklis, J., Bertsekas, D., & Athans, M. (1986) · IEEE Transactions on Automatic Control · doi:10.1109/tac.1986.1104412 · Cited by 1,967
Our Data, Ourselves: Privacy Via Distributed Noise Generation
Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., & Naor, M. (2006) · Lecture Notes in Computer Science · doi:10.1007/11761679_29 · Cited by 1,835
Differentially Private Empirical Risk Minimization
Chaudhuri, K., Monteleoni, C., & Sarwate, A. (2009) · Journal of machine learning research · doi:10.5555/1953048.2021036 · Cited by 1,634 · cited 1×
“In [1, 9] the authors solve a privacy preserving optimization problem with two methods: output perturbation and objective perturbation.”
Method(2011) · PubMed · Cited by 990 · cited 1×
“In [1, 9] the authors solve a privacy preserving optimization problem with two methods: output perturbation and objective perturbation.”
MethodGradient methods for minimizing composite objective function
Nesterov, Y. E. (2007) · Cited by 867
Distributed Stochastic Subgradient Projection Algorithms for Convex Optimization
Sundhar Ram, S., Nedić, A., & Veeravalli, V. V. (2010) · Journal of Optimization Theory and Applications · doi:10.1007/s10957-010-9737-7 · Cited by 814 · cited 1×
“Categories and Subject Descriptors D.1.3 [Software]: Concurrent Programming—Distributed programming General Terms Algorithm Keywords Distributed Optimization, Differential Privacy, Iterative Consensus”
BackgroundInfluential
Research works printed but not linked: 1
- 10.5555/1791834.1791836 · doi:10.5555/1791834.1791836
Cited by
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
Federated learning of predictive models from federated Electronic Health Records
Brisimi, T. S., Chen, R., Mela, T., Olshevsky, A., Paschalidis, I. C., & Shi, W. (2018) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2018.01.007 · Cited by 997
Secure and Privacy-Preserving Consensus
Ruan, M., Gao, H., & Wang, Y. (2019) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2019.2890887 · Cited by 347
“ng and control systems such as power systems and wireless sensor networks. To address the pressing need for privacy and security in consensus, recently, several solutions have been proposed [6], [7], [8], [9], [10], [11], [12], [13]. Most of these approaches use the idea of obfuscation to mask the true state values by…”
BackgroundMethodDifferentially private average consensus: Obstructions, trade-offs, and optimal algorithm design
Nozari, E., Tallapragada, P., & Cortés, J. (2017) · Automatica · doi:10.1016/j.automatica.2017.03.016 · Cited by 334
“O C ] 2 8 Fe b 20 17 et al., 2012, 2014, Wang et al., 2014], estimation [Ny and Pappas, 2014], and optimization [Han et al., 2014, Huang et al., 2015, Nozari et al., 2017].”
Privacy-Preserving Average Consensus via State Decomposition
Wang, Y. (2019) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2019.2902731 · Cited by 334
“Onecommonlyusedtoolis differentialprivacyfromthedatabaseliteratureincomputerscience [10],[11]–[15].”
Differentially Private Distributed Constrained Optimization
Han, S., Topcu, U., & Pappas, G. J. (2017) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2016.2541298 · Cited by 292
“In their formulation, the private user information is encodedin the individual cost functions and can be interpreted as user preferences.”
BackgroundDifferential privacy in control and network systems
Cortes, J., Dullerud, G. E., Han, S., Le Ny, J., Mitra, S., & Pappas, G. J. (2016) · 2016 IEEE 55th Conference on Decision and Control (CDC) · doi:10.1109/cdc.2016.7798915 · Cited by 220
“In fact, this is the algorithm considered in [28].”
BackgroundSelf-citationADMM Based Privacy-Preserving Decentralized Optimization
Zhang, C., Ahmad, M., & Wang, Y. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2855169 · Cited by 206
“Comparison with the algorithm in [19] We then compared our approach with the differentialprivacy based privacy-preserving optimization algorithm in [19].”
BackgroundMethodResultInfluentialDP-ADMM: ADMM-Based Distributed Learning With Differential Privacy
Huang, Z., Hu, R., Guo, Y., Chan-Tin, E., & Gong, Y. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2931068 · Cited by 190
“Among the works on distributed learning with differential privacy, most of them focus on subgradient-based algorithms [35]–[38] and only a few works consider ADMMbased methods [1], [2], [17]–[19].”
BackgroundSelf-citationDifferentially Private Distributed Convex Optimization via Functional Perturbation
Nozari, E., Tallapragada, P., & Cortes, J. (2018) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2016.2614100 · Cited by 182
“Of more relevance to our paper are recent works [17]–[19] that are focused on differentially private distributed optimization problems for multi-agent systems.”
BackgroundMethodInfluentialThe Value of Collaboration in Convex Machine Learning with Differential Privacy
Wu, N., Farokhi, F., Smith, D., & Kaafar, M. A. (2020) · 2020 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp40000.2020.00025 · Cited by 122
Resilient consensus for multi-agent systems subject to differential privacy requirements
Fiore, D., & Russo, G. (2019) · Automatica · doi:10.1016/j.automatica.2019.04.029 · Cited by 137
“…of differential privacy has been also successfully used in distributed estimation (Le Ny and Pappas, 2014) and optimization (Han et al., 2014; Huang et al., 2015; Nozari et al., 2018), while other notions of privacy, see (Mo and Murray, 2017) and references therein for further details, have…”
MethodMao, S., Tang, Y. S., Dong, Z., Meng, K., Dong, Z. Y., & Qian, F. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2996198 · Cited by 135
“Toenable the privacy preservation for EDPs over directed communicationnetworks,withoutcompromisingtheoptimality, suchas[17],[18],and[23],anoveldistributedoptimization approachisproposedinthisarticlebycombiningconditional noises[24]withthepush-(sub)gradientmethod[25].”
BackgroundMethodInfluentialResilient Consensus of Discrete-Time Complex Cyber-Physical Networks Under Deception Attacks
Fu, W., Qin, J., Shi, Y., Zheng, W. X., & Kang, Y. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2933596 · Cited by 135
“In [11] and [12], the differential-privacy-based approach was applied to solve the consensus problems by adding uncorrelated noise.”
MethodDing, T., Zhu, S., He, J., Chen, C., & Guan, X. (2021) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2021.3059427 · Cited by 126
Privacy-Preserving Consensus-Based Energy Management in Smart Grids
Zhao, C., Chen, J., He, J., & Cheng, P. (2018) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2018.2872817 · Cited by 121
Differentially Private Distributed Online Learning
Li, C., Zhou, P., Xiong, L., Wang, Q., & Wang, T. (2018) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2794384 · Cited by 116
“, [7], [8], [9]).”
Preserving Data-Privacy With Added Noises: Optimal Estimation and Privacy Analysis
He, J., Cai, L., & Guan, X. (2018) · IEEE Transactions on Information Theory · doi:10.1109/tit.2018.2842221 · Cited by 116
Enabling Privacy-Preservation in Decentralized Optimization
Zhang, C., & Wang, Y. (2019) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2018.2873152 · Cited by 124
“To enable privacy-preservation in decentralized optimization, one commonly used approach is differential privacy [6], [23]–[27], which adds carefully designed noise to exchanged”
BackgroundMethodInfluentialA Survey on Differentially Private Machine Learning [Review Article]
Gong, M., Xie, Y., Pan, K., Feng, K., & Qin, A. K. (2020) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2020.2976185 · Cited by 115
“[61] proposed a private distributed optimization problem (PDOP) based on objective perturbation, which effectively provides privacy pre serving for the objective function of each agent.”
BackgroundWang, Y., Huang, Z., Mitra, S., & Dullerud, G. E. (2017) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2017.2658190 · Cited by 111
“More recently, the notion of differential privacy has been extended to dynamical systems [17], [25] and applied to various problems, such as distributed consensus protocols [17], [26]–[28], distributed optimization [29]–[32], and filtering [18], [25], [33].”
BackgroundSelf-citationTailoring Gradient Methods for Differentially Private Distributed Optimization
Wang, Y., & Nedić, A. (2023) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2023.3272968 · Cited by 138
Differential Private Noise Adding Mechanism and Its Application on Consensus Algorithm
He, J., Cai, L., & Guan, X. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.3006760 · Cited by 120
“In [27], the authors solved distributed consensus problems while keeping the agents’ objective functions private, and in [26] the same authors solved similar problems while keeping the privacy of each agent’s initial state.”
BackgroundDifferentially Private Distributed Nash Equilibrium Seeking for Aggregative Games
Ye, M., Hu, G., Xie, L., & Xu, S. (2021) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2021.3075183 · Cited by 107
Privacy-aware quadratic optimization using partially homomorphic encryption
Shoukry, Y., Gatsis, K., Alanwar, A., Pappas, G. J., Seshia, S. A., Srivastava, M. B., & Paulo Tabuada, B. (2016) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2016.7799042 · Cited by 103
“That is, to provide higher privacy guarantees a protocol needs to add more noise, resulting in the final output differing significantly from the desired optimal solution [3], [5], and thus affecting the usability of the output.”
BackgroundRecycled ADMM: Improving the Privacy and Accuracy of Distributed Algorithms
Zhang, X., Khalili, M. M., & Liu, M. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2947867 · Cited by 107
Plis, S. M., Sarwate, A. D., Wood, D., Dieringer, C., Landis, D., Reed, C., Panta, S. R., Turner, J. A., Shoemaker, J. M., Carter, K. W., et al. (2016) · Frontiers in Neuroscience · doi:10.3389/fnins.2016.00365 · Cited by 102
“…some general algorithms have been proposed that work on the principle of averaging the outputs of computations from local data (Wang et al., 2013; Huang et al., 2014; Ji et al., 2014; Song et al., 2015); a recent study by the authors found that differentially private aggregation of local…”
BackgroundDifferentially Private Distributed Online Algorithms Over Time-Varying Directed Networks
Zhu, J., Xu, C., Guan, J., & Wu, D. O. (2018) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2018.2797806 · Cited by 101
“This assumption is also considered in [28], where the graph is undirected.”
BackgroundXiong, Y., Xu, J., You, K., Liu, J., & Wu, L. (2020) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2020.2976273 · Cited by 101
“Following the line of Lemma 2 in [38], we can obtain that”
MethodDifferentially Private Consensus With an Event-Triggered Mechanism
Gao, L., Deng, S., & Ren, W. (2018) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2018.2795703 · Cited by 98
“Then, relevant problems including filtering estimation [19] and distributed optimization [20], [21] have been further studied in recent years.”
BackgroundCloud-Based Quadratic Optimization With Partially Homomorphic Encryption
Alexandru, A. B., Gatsis, K., Shoukry, Y., Seshia, S. A., Tabuada, P., & Pappas, G. J. (2020) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2020.3005920 · Cited by 108
“This approach lies out of the scope of our paper, but works such as [42]–[44] may be helpful to this end.”
BackgroundPrivacy Preservation in Distributed Subgradient Optimization Algorithms
Lou, Y., Yu, L., Wang, S., & Yi, P. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2728644 · Cited by 101
Differentially Private Average Consensus with Optimal Noise Selection
Nozari, E., Tallapragada, P., & Cortés, J. (2015) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2015.10.331 · Cited by 87
“, 2014), estimation (Ny and Pappas, 2014), and optimization (Han et al., 2014; Huang et al., 2015).”
Design of Privacy-Preserving Dynamic Controllers
Kawano, Y., & Cao, M. (2020) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2020.2994030 · Cited by 77
Differentially private cloud-based multi-agent optimization with constraints
Hale, M., & Egerstedty, M. (2015) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.1109/acc.2015.7170902 · Cited by 78
“In [11], the authors solve a distributed optimization problem in which the agents’ objective functions must be kept private.”
BackgroundMitridati, L., Kazempour, J., & Pinson, P. (2019) · Omega · doi:10.1016/j.omega.2019.102177 · Cited by 74
Differentially Private Consensus With Quantized Communication
Gao, L., Deng, S., Ren, W., & Hu, C. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2890645 · Cited by 64
Cloud-Enabled Differentially Private Multiagent Optimization With Constraints
Hale, M., & Egerstedt, M. (2017) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2017.2751458 · Cited by 67
“In the multiagent setting, [23] solves distributed consensus-type problems while keeping the agents’ objective functions private, whereas [24] solves similar problems while keeping each agent’s initial state private.”
BackgroundMulti-Armed Bandits with Local Differential PrivacyPreprint
Ren, W., Zhou, X., Liu, J., & Shroff, N. B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.03121 · Cited by 68
“DP algorithms have been studied in many areas, such as data release [20], optimization [14], and Q-learning [26], just to name a few.”
BackgroundPrivacy-Preserving Distributed Optimization via Subspace Perturbation: A General Framework
Li, Q., Heusdens, R. R., & Christensen, M. G. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.3029887 · Cited by 68
“This method of protecting private data has been applied in [10]–[16] through carefully adding noise to the exchanged states or objective functions.”
MethodQuantization Enabled Privacy Protection in Decentralized Stochastic Optimization
Wang, Y., & Başar, T. (2022) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2022.3198030 · Cited by 79
“For example, in decentralized-optimization based localization, disclosing the gradient of an agent amounts to disclosing its position [24], [35].”
Differential Privacy in Distributed Optimization With Gradient Tracking
Huang, L., Wu, J., Shi, D., Dey, S., & Shi, L. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2024.3352328 · Cited by 78
“If one has (cid:9)∇ f i ( x ) (cid:9) 1 ≤ c ∀ i ∈ N , as assumed in [16], one always has (cid:9)∇ f i 0 ( x ) − ∇ f i 0 ( x ) (cid:9) 1 ≤ (cid:9)∇ f i 0 ( x ) (cid:9) 1 + (cid:9)∇ f i 0 ( x ) (cid:9) 1 ≤ δ by letting δ = 2 c .”
BackgroundMethodInfluentialSecure and Privacy-Preserving Average Consensus
Ruan, M., Ahmad, M., & Wang, Y. (2017) · Workshop on Cyber-Physical Systems Security and PrivaCy (CPS-SPC) · doi:10.1145/3140241.3140243 · Cited by 66
Sun, L., Ding, D., Dong, H., & Bai, X. (2023) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2023.3324138 · Cited by 56
“…3 [17]: Letting δ > 0 be a constant, two vectors a and b are said to be δ -adjacent if there exists an element i in them such that Definition 4 [13]: For ζ( 0 ) and ζ (cid:14) ( 0 ) being two δ -adjacent initial variables, Algorithm (4) can guarantee (cid:24) -differential privacy if, for any…”
BackgroundChen, X., Huang, L., He, L., Dey, S., & Shi, L. (2023) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2023.3264932 · Cited by 55
“Owingtotheunbalancedinterac-tions over agents, the approaches in [14], [15], and [16] fail to guarantee convergence in such scenarios.”
BackgroundPrivacy-Preserving Distributed Processing: Metrics, Bounds and Algorithms
Li, Q., Gundersen, J. S., Heusdens, R. R., & Christensen, M. G. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3050064 · Cited by 52
Differentially Private Distributed Algorithms for Aggregative Games With Guaranteed Convergence
Wang, Y., & Nedić, A. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2024.3351068 · Cited by 49
“(ǫ-differential privacy, adapted from [32]).”
BackgroundMethodInfluentialDifferentially private distributed convex optimization via objective perturbation
Nozari, E., Tallapragada, P., & Cortés, J. (2016) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.1109/acc.2016.7525222 · Cited by 56
“More closely related to our present work are efforts [16]–[18] on differentially private distributed optimization for networked systems, where the sensitive information are the objective functions in [16], the optimization constraints in [17], and the agents’ states in [18].”
BackgroundDecentralized Stochastic Optimization With Inherent Privacy Protection
Wang, Y., & Poor, H. V. (2022) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2022.3174187 · Cited by 59
“For example, in sensor network based localization, the positions of sensor agents should be kept private in sensitive (hostile) environments [45], [52].”
BackgroundEnhancement of opacity for distributed state estimation in cyber–physical systems
An, L., & Yang, G. (2021) · Automatica · doi:10.1016/j.automatica.2021.110087 · Cited by 46
Asynchronous Federated Learning with Differential Privacy for Edge IntelligencePreprint
Li, Y., Yang, S., Ren, X., & Zhao, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.07902 · Cited by 53
“DP can be usually achieved by adding a noise vector η [50], [51] to the gradient.”
BackgroundResultFederated learning-based disease prediction: A fusion approach with feature selection and extraction
Kapila, R., & Saleti, S. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106961 · Cited by 50
On privacy vs. cooperation in multi-agent systems
Katewa, V., Pasqualetti, F., & Gupta, V. (2017) · International Journal of Control · doi:10.1080/00207179.2017.1326632 · Cited by 44
“In Huang et al. (2015) and Han et al. (2014), the authors study distributed convex optimisation and optimisation with piecewise affine objectives, respectively, and develop DP mechanisms to keep the agents’ cost functions private.”
BackgroundPrivacy-Preserving Average Consensus on Directed Graphs Using Push-Sum
Gao, H. B., Zhang, C., Ahmad, M., & Wang, Y. (2018) · IEEE Conference on Communications and Network Security · doi:10.1109/cns.2018.8433217 · Cited by 52
Privacy in Control and Dynamical Systems
Han, S., & Pappas, G. J. (2018) · Annual Review of Control Robotics and Autonomous Systems · doi:10.1146/annurev-control-060117-105018 · Cited by 56
Differentially Private Distributed Resource Allocation via Deviation Tracking
Ding, T., Zhu, S., Chen, C., Xu, J., & Guan, X. (2021) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2021.3062985 · Cited by 41
“However, both [18] and [19] use decaying stepsizes to maintain the convergence, which results in a low convergence rate.”
BackgroundMethodInfluentialDifferentially Private Distributed Optimization With an Event-Triggered Mechanism
Mao, S., Yang, M., Yang, W. D., Tang, Y. S., Zheng, W. X., Gu, J., & Werner, H. (2023) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2023.3266358 · Cited by 40
“The differentially private distributed convex optimization problems were studied in [14], where private individual information is encoded in local cost functions.”
BackgroundPrivacy-Preserving Incremental ADMM for Decentralized Consensus Optimization
Ye, Y., Chen, H., Xiao, M., Skoglund, M., & Poor, H. V. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.3027917 · Cited by 39
“Differential private distributed algorithms based on GD have been presented in [30]–[32], where noise following different distributions is added to variable or gradients.”
MethodPrivate Optimization on Networks
Gade, S., & Vaidya, N. H. (2018) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc.2018.8430960 · Cited by 46
“-differential privacy is a probabilistic technique that involves use of randomized perturbations [26]–[30] to minimize the probability of uncovering of specific records from databases.”
BackgroundSelf-citationDistributed Mechanism Design for Network Resource Allocation Problems
Heydaribeni, N., & Anastasopoulos, A. (2019) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2019.2923959 · Cited by 37
“, adding noise to) the exchanged messages or the objective function as in [37]–[40].”
BackgroundPrivacy-Preserving Distributed Kalman Filtering
Moradi, A., Venkategowda, N. K. D., Talebi, S. P., & Werner, S. (2022) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2022.3182590 · Cited by 37
“The literature contains various methods that address the privacy issues in distributed processing problems, such as consensus [25]–[32], [34], optimization [22], [23], filtering [24], and state estimation [35]–[44].”
BackgroundDynamics based privacy preservation in decentralized optimization
Gao, H. B., Wang, Y., & Nedić, A. (2023) · Automatica · doi:10.1016/j.automatica.2023.110878 · Cited by 44
“We ran the algorithm in [15] under four different privacy levels, i.”
BackgroundMethodResultInfluentialDifferential private noise adding mechanism: Basic conditions and its application
He, J., & Cai, L. (2017) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc.2017.7963193 · Cited by 36
“Differential privacy has attracted substantial attention throughout computer, control and communication science, including areas like deep learning [9], optimization [6]– [8], dynamic systems [18] and more [11], [12].”
BackgroundDifferentially private convex optimization with piecewise affine objectives
Han, S., Topcu, U., & Pappas, G. J. (2014) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2014.7039718 · Cited by 36
Gradual Release of Sensitive Data under Differential Privacy
Koufogiannis, F., Han, S., & Pappas, G. J. (2017) · Journal of Privacy and Confidentiality · doi:10.29012/jpc.v7i2.649 · Cited by 43
Yang, Y., He, W., Du, W., Tian, Y., Han, Q., & Qian, F. (2024) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3357253 · Cited by 33
“…noise was injected to the exchanged states to avoid the function disclosure in a class of privacy-preserving distributed constrained optimization [31], which has been extended to distributed online optimization over balanced [32] and unbalanced [33], [34] networks while only the sublinear…”
BackgroundDifferentially Private ADMM for Regularized Consensus Optimization
Cao, X., Zhang, J., Poor, H. V., & Tian, Z. (2020) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2020.3022856 · Cited by 38
Fully privacy-preserving distributed optimization in power systems based on secret sharing
Tian, N., Guo, Q., Sun, H., & Zhou, X. (2022) · iEnergy · doi:10.23919/ien.2022.0045 · Cited by 33
Privacy-Preserved Distributed Learning With Zeroth-Order Optimization
Gratton, C., Venkategowda, N. K. D., Arablouei, R., & Werner, S. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3139267 · Cited by 41
“The authors of [22]–[24] propose differentially-private distributed algorithms that utilize the projected-gradient-descent method for handling constraints.”
BackgroundDifferentially private containment control for multi-agent systems
Yang, Z., Liu, Y.-R., Zhang, W.-B., Alsaadi, F., & Alharbi, K. H. (2022) · International Journal of Systems Science · doi:10.1080/00207721.2022.2070794 · Cited by 22
“…works have been carried out, including maximum (minimum) consensus (X. Wang et al., 2019), resilient consensus (Fiore & Russo, 2019), event-triggered consensus (Gao et al., 2019; A. Wang et al., 2019), optimal noise selection (Nozari et al., 2015) and distributed optimization (Huang et al., 2015).”
BackgroundDecentralized nonconvex optimization with guaranteed privacy and accuracy
Wang, Y., & Başar, T. (2023) · Automatica · doi:10.1016/j.automatica.2023.110858 · Cited by 40
Detection of anomalous vehicle trajectories using federated learning
Koetsier, C., Fiosina, J., Gremmel, J. N., Müller, J. P., Woisetschläger, D. M., & Sester, M. (2022) · ISPRS Open Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.ophoto.2022.100013 · Cited by 31
A Distributed-Optimization-Based Architecture for Management of Interconnected Energy Hubs
Ferro, G., Robba, M., Haider, R., & Annaswamy, A. M. (2022) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2022.3165022 · Cited by 31
Yu, X., & Wang, Y. (2023) · Automatica · doi:10.1016/j.automatica.2023.111150 · Cited by 35
Secure Federated Evolutionary Optimization—A Survey
Liu, Q., Yan, Y., Jin, Y., Wang, X., Ligeti, P., Yu, G., & Yan, X. (2023) · Engineering · doi:10.1016/j.eng.2023.10.006 · Cited by 30
Algorithm-Level Confidentiality for Average Consensus on Time-Varying Directed Graphs
Gao, H. B., & Wang, Y. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3140274 · Cited by 30
Privacy-Preserved Distributed Optimization for Multi-Agent Systems With Antagonistic Interactions
Luo, Q., Liu, S., Wang, L., & Tian, E. (2022) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2022.3226578 · Cited by 28
“As another alternative method, very recently, the differential privacy algorithm [37], [38], [39], [40] has appealed to considerable attention and obtained successful applications due to its exact mathematical framework and ease of implementation.”
MethodA brief survey on encrypted control: From the first to the second generation and beyond
Schlüter, N., Binfet, P., & Darup, M. S. (2023) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2023.100913 · Cited by 40
Ding, T., Zhu, S., He, J., Chen, C., & Guan, X. (2018) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2018.8619119 · Cited by 28
“The algorithm proposed in [14] is performed with a decaying stepsize, which causes a low convergence rate.”
MethodInfluentialWang, Y., & Nedić, A. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2024.3385546 · Cited by 36
“Different from [11] and [53] that restrict all gradients to be uniformly bounded, and [54] that restricts the gradient difference to be uniformly bounded, we add the second condition, which, as shown later, together with the proposed noise-robust algorithm, allows us to ensure rigorous DP while…”
BackgroundMethodInfluentialDifferentially Private Consensus and Distributed Optimization in Multi-Agent Systems: A Review
Wang, Y., Lin, H. S., Lam, J., & Kwok, K. (2023) · Neurocomputing · doi:10.1016/j.neucom.2024.127986 · Cited by 26
Modular control under privacy protection: Fundamental trade-offs
Kawano, Y., Kashima, K., & Cao, M. (2021) · Automatica · doi:10.1016/j.automatica.2021.109518 · Cited by 26
Decentralized Parallel SGD With Privacy Preservation in Vehicular Networks
Yu, D., Zou, Z., Chen, S., Tao, Y., Tian, B., Lv, W., & Cheng, X. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3064877 · Cited by 26
“Huang et al. [31] presented a distributed algorithm to solve the consensus problem.”
MethodPrivacy Preserving Consensus-Based Economic Dispatch in Smart Grid Systems
Mandal, A. (2016) · Communications in computer and information science · doi:10.1007/978-3-319-48021-3_7 · Cited by 26
Differential privacy of populations in routing games
Dong, R., Krichene, W., Bayen, A. M., & Sastry, S. (2015) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2015.7402640 · Cited by 31
“This definition was originally designed for databases taking values in a finite alphabet, but has since been extended to consider the output of optimization algorithms [16], [17], [18], [19] and dynamical systems [20].”
BackgroundRobust Decentralized Low-Rank Matrix Decomposition
Hegedűs, I., Berta, Á., Kocsis, L., Benczúr, A. A., & Jelasity, M. (2016) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/2854157 · Cited by 25
Privacy Preservation in Distributed Optimization via Dual Decomposition and ADMM
Tjell, K., & Wisniewski, R. (2019) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc40024.2019.9028969 · Cited by 25
“There is also a substantial amount of work, basing the privacy preservation on differential privacy, for instance [5], [6], and [7].”
BackgroundLv, Y.-W., Yang, G., & Shi, C. (2020) · Information Sciences · doi:10.1016/j.ins.2020.05.119 · Cited by 27
Differential privacy for symbolic systems with application to Markov Chains
Chen, B., Leahy, K., Jones, A. M., & Hale, M. (2023) · Automatica · doi:10.1016/j.automatica.2023.110908 · Cited by 24
Recycled ADMM: Improve Privacy and Accuracy with Less Computation in Distributed Algorithms
Zhang, X., Khalili, M. M., & Liu, M. (2018) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton.2018.8635916 · Cited by 31
Privacy Amplification by Decentralization
Cyffers, E., & Bellet, A. (2020) · arXiv · doi:10.48550/arxiv.2012.05326 · Cited by 23
“In LDP, random perturbations are performed locally by each user, making it convenient to design private versions of fully de-centralized algorithms in this model (see e.g., Huang et al., 2015; Bellet et al., 2018; Li et al., 2018; Cheng et al., 2019; Zhang et al., 2018; Xu et al., 2020).”
MethodAnonymous Privacy-Preserving Consensus via Mixed Encryption Communication
Feng, Y., Wang, F., Duan, F., Liu, Z., & Chen, Z. (2022) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2022.3144389 · Cited by 25
Dong, T., Bu, X., & Hu, W. (2020) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2019.12.027 · Cited by 23
Xu, Q., Yu, C., Yuan, X., Fu, Z., & Liu, H. (2022) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2022.106028 · Cited by 20
“For instance, as claimed in [8], the smart grids linked through such direct message communications may be tender for adversaries to attack the grid system effectively.”
BackgroundWang, Y., & Nedić, A. (2023) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2023.3348158 · Cited by 28
“For example, differential-privacy based approaches have been proposed to obscure shared information in decentralized optimization by injecting noise to exchanged messages [20], [24], [25], [26] or objective functions [27].”
BackgroundDifferentially private objective functions in distributed cloud-based optimization
Wang, Y., Hale, M., Egerstedt, M., & Dullerud, G. E. (2016) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2016.7798824 · Cited by 20
“Recently, there has been increased interest in applying the concept of differential privacy in the context of distributed optimization [15], [16], [17], [18].”
BackgroundPrivacy preserving cloud-based quadratic optimization
Alexandru, A. B., Gatsis, K., & Pappas, G. J. (2017) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton.2017.8262869 · Cited by 22
“[10], [11].”
A Study of Privacy Preservation in Average Consensus Algorithm via Deterministic Obfuscation Signals
Rezazadeh, N., & Kia, S. S. (2023) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2023.3290114 · Cited by 19
“Additive obfuscation noises have also been used as a privacy preservation mechanism in other distributed algorithms such as distributed optimization [11]; distributed estimation [12], [13]; and distributed games [14].”
MethodPrivacy-Preserving Push-Pull Method for Decentralized Optimization via State Decomposition
Cheng, H., Liao, X., Li, H., Lü, Q., & Zhao, Y. (2024) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2024.3402430 · Cited by 25
“However, if the problem is solved directly using a gradient-based rendezvous algorithm, it may lead to the exposure of the agents’ initial positions without employing appropriate privacy mechanisms [28].”
BackgroundDifferentially Private Gossip Gradient Descent
Liu, Y., Liu, J., & Başar, T. (2018) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2018.8619437 · Cited by 19
“The privacy issue has been considered in average consensus [21], [22], distributed optimization [23], [24], and linear distributed control systems [25].”
Background
Metadata
- Authors
- Huang, Z., Mitra, S., & Vaidya, N.
- Affiliations
- University of Illinois Urbana-Champaign (US)
- Venue
- Proceedings of the 16th International Conference on Distributed Computing and Networking
- Publisher
- ACM
- Published
- 2015-01-04
- Pages
- 1-10
- OpenAlex
- W2092845654
- Cited by
- 266
- References
- 17
- Citations by year
- 2026: 15 · 2025: 24 · 2024: 37 · 2023: 33 · 2022: 27 · 2021: 24 · 2020: 23 · 2019: 26 · 2018: 23 · 2017: 14 · 2016: 12 · 2015: 5
- FWCI
- 10.14
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- International Conference on Distributed Computing and Networking (ICDCN) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (CAREER CNS 10-54247)
- NSA (SoS W911NSF-13-0086)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems
- Physical Sciences › Computer Science › Computer Networks and Communications › Distributed Sensor Networks and Detection Algorithms
- Keywords
- differential privacy, distributed optimization, multi-agent systems, privacy-accuracy trade-off, convergence analysis, iterative methods, privacy-preserving optimization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.