Detection of Insider Attacks in Distributed Projected Subgradient Algorithms

The gossip-based distributed algorithms are widely used to solve decentralized optimization problems in various multi-agent applications, while they are generally vulnerable to data injection attacks by internal malicious agents as each agent locally estimates its decent direction without an authorized supervision. In this work, we explore the application of artificial intelligence (AI) technologies to detect internal attacks. We show that a general neural network is particularly suitable for detecting and localizing the malicious agents, as they can effectively explore nonlinear relationship underlying the collected data. Moreover, we propose to adopt one of the state-of-art approaches in federated learning, i.e., a collaborative peer-topeer machine learning protocol, to facilitate training our neural network models by gossip exchanges. This advanced approach is expected to make our model more robust to challenges with insufficient training data, or mismatched test data. In our simulations, a least-squared problem is considered to verify the feasibility and effectiveness of AI-based methods. Simulation results demonstrate that the proposed AI-based methods are beneficial to improve performance of detecting and localizing malicious agents over score-based methods, and the peer-to-peer neural network model is indeed robust to target issues.

[1]  M. Mobilia.  Does a single zealot affect an infinite group of voters? , 2003, Physical review letters.

[2]  Marimuthu Palaniswami,et al.  Distributed Real-Time IoT for Autonomous Vehicles , 2019, IEEE Transactions on Industrial Informatics.

[3]  Asuman E. Ozdaglar,et al.  Constrained Consensus and Optimization in Multi-Agent Networks , 2008, IEEE Transactions on Automatic Control.

[4]  Tomasz Bednarz,et al.  Discovery of Malicious Nodes in Wireless Sensor Networks Using Neural Predictors , 2007 .

[5]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  David Gesbert,et al.  Adaptation, Coordination, and Distributed Resource Allocation in Interference-Limited Wireless Networks , 2007, Proceedings of the IEEE.

[7]  Anna Scaglione,et al.  Detection of data injection attacks in decentralized learning , 2015, 2015 49th Asilomar Conference on Signals, Systems and Computers.

[8]  Ming Li,et al.  Vulnerability and protection for distributed consensus-based spectrum sensing in cognitive radio networks , 2012, 2012 Proceedings IEEE INFOCOM.

[9]  Anna Scaglione,et al.  Data Injection Attack on Decentralized Optimization , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10]  Soung Chang Liew,et al.  Deep-Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks , 2017, 2018 IEEE International Conference on Communications (ICC).

[11]  Danijela Cabric,et al.  Distributed Wideband Sensing-Based Architecture for Unlicensed Massive IoT Communications , 2018, IEEE Transactions on Cognitive Communications and Networking.

[12]  Anna Scaglione,et al.  Detection and Isolation of Adversaries in Decentralized Optimization for Non-Strongly Convex Objectives , 2019, ArXiv.

[13]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[14]  Shreyas Sundaram,et al.  Consensus-based distributed optimization with malicious nodes , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[15]  Yongqiang Wang,et al.  Enabling Privacy-Preservation in Decentralized Optimization , 2019, IEEE Transactions on Control of Network Systems.

[16]  Pramod K. Varshney,et al.  Consensus based Detection in the Presence of Data Falsification Attacks , 2015, ArXiv.

[17]  Qiang Li,et al.  Detect Insider Attacks Using CNN in Decentralized Optimization , 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[18]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[19]  Chung-Horng Lung,et al.  DDoS Attacks Detection and Mitigation in SDN Using Machine Learning , 2019, 2019 IEEE World Congress on Services (SERVICES).

[20]  Sourav Patel,et al.  Distributed Detection of Malicious Attacks on Consensus Algorithms with Applications in Power Networks , 2020, 2020 7th International Conference on Control, Decision and Information Technologies (CoDIT).

[21]  Angelia Nedic,et al.  Distributed Stochastic Subgradient Projection Algorithms for Convex Optimization , 2008, J. Optim. Theory Appl..

[22]  Asuman E. Ozdaglar,et al.  Distributed Subgradient Methods for Multi-Agent Optimization , 2009, IEEE Transactions on Automatic Control.

[23]  Rasmus Berg Palm,et al.  Prediction as a candidate for learning deep hierarchical models of data , 2012 .

[24]  Qiang Li,et al.  Neural Networks-Aided Insider Attack Detection for the Average Consensus Algorithm , 2020, IEEE Access.

[25]  Lodovico Giaretta,et al.  Gossip Learning: Off the Beaten Path , 2019, 2019 IEEE International Conference on Big Data (Big Data).

[26]  John N. Tsitsiklis,et al.  Problems in decentralized decision making and computation , 1984 .

[27]  Anna Scaglione,et al.  Detection of Data Injection Attacks on Decentralized Statistical Estimation , 2018, 2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE).

[28]  Anna Scaglione,et al.  A Review of Distributed Algorithms for Principal Component Analysis , 2018, Proceedings of the IEEE.

[29]  Anna Scaglione,et al.  Detecting and Localizing Adversarial Nodes Usig Neural Networks , 2018, 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[30]  Jiming Chen,et al.  Resilient Consensus with Mobile Detectors Against Malicious Attacks , 2018, IEEE Transactions on Signal and Information Processing over Networks.

[31]  Georgios B. Giannakis,et al.  Monitoring and Optimization for Power Grids: A Signal Processing Perspective , 2013, IEEE Signal Processing Magazine.

[32]  Abdullah Al-Dujaili,et al.  AST-Based Deep Learning for Detecting Malicious PowerShell , 2018, CCS.

[33]  Yitao Liu,et al.  Deep Learning-Based Interval State Estimation of AC Smart Grids Against Sparse Cyber Attacks , 2018, IEEE Transactions on Industrial Informatics.

[34]  B. Gharesifard,et al.  Distributed Optimization Under Adversarial Nodes , 2016, IEEE Transactions on Automatic Control.

[35]  Pramod K. Varshney,et al.  Data Falsification Attacks on Consensus-Based Detection Systems , 2017, IEEE Transactions on Signal and Information Processing over Networks.

[36]  Chinmay Hegde,et al.  Collaborative Deep Learning in Fixed Topology Networks , 2017, NIPS.

[37]  István Hegedüs,et al.  Gossip learning with linear models on fully distributed data , 2011, Concurr. Comput. Pract. Exp..

[38]  Abhinav Vishnu,et al.  GossipGraD: Scalable Deep Learning using Gossip Communication based Asynchronous Gradient Descent , 2018, ArXiv.

[39]  István Hegedüs,et al.  Gossip Learning as a Decentralized Alternative to Federated Learning , 2019, DAIS.

[40]  Jia Zhou,et al.  A Survey of Intrusion Detection for In-Vehicle Networks , 2020, IEEE Transactions on Intelligent Transportation Systems.

[41]  Monica Nicoli,et al.  Federated Learning With Cooperating Devices: A Consensus Approach for Massive IoT Networks , 2019, IEEE Internet of Things Journal.

[42]  Matthieu Cord,et al.  GoSGD: Distributed Optimization for Deep Learning with Gossip Exchange , 2018, Neurocomputing.

[43]  Anna Scaglione,et al.  Data Injection Attacks in Randomized Gossiping , 2016, IEEE Transactions on Signal and Information Processing over Networks.