Mitigating Data Poisoning Attacks On a Federated Learning-Edge Computing Network

Edge Computing (EC) has seen a continuous rise in its popularity as it provides a solution to the latency and communication issues associated with edge devices transferring data to remote servers. EC achieves this by bringing the cloud closer to edge devices. Even though EC does an excellent job of solving the latency and communication issues, it does not solve the privacy issues associated with users transferring personal data to the nearby edge server. Federated Learning (FL) is an approach that was introduced to solve the privacy issues associated with data transfers to distant servers. FL attempts to resolve this issue by bringing the code to the data, which goes against the traditional way of sending the data to remote servers. In FL, the data stays on the source device, and a Machine Learning (ML) model used to train the local data is brought to the end device instead. End devices train the ML model using local data and then send the model updates back to the server for aggregation. However, this process of asking random devices to train a model using its local data has potential risks such as a participant poisoning the model using malicious data for training to produce bogus parameters. In this paper, an approach to mitigate data poisoning attacks in a federated learning setting is investigated. The application of the approach is highlighted, and the practical and secure nature of this approach is illustrated as well using numerical results.

[1]  Tudor Dumitras,et al.  When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks , 2018, USENIX Security Symposium.

[2]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[3]  Danda B. Rawat,et al.  IFLBC: On the Edge Intelligence Using Federated Learning Blockchain Network , 2020, 2020 IEEE 6th Intl Conference on Big Data Security on Cloud (BigDataSecurity), IEEE Intl Conference on High Performance and Smart Computing, (HPSC) and IEEE Intl Conference on Intelligent Data and Security (IDS).

[4]  Vitaly Shmatikov,et al.  How To Backdoor Federated Learning , 2018, AISTATS.

[5]  Ling Huang,et al.  ANTIDOTE: understanding and defending against poisoning of anomaly detectors , 2009, IMC '09.

[6]  Dawn Xiaodong Song,et al.  Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning , 2017, ArXiv.

[7]  Ivor W. Tsang,et al.  On the Convergence of a Family of Robust Losses for Stochastic Gradient Descent , 2016, ECML/PKDD.

[8]  Luis Muñoz-González,et al.  Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection , 2018, ArXiv.

[9]  Percy Liang,et al.  Certified Defenses for Data Poisoning Attacks , 2017, NIPS.

[10]  Ivan Beschastnikh,et al.  Mitigating Sybils in Federated Learning Poisoning , 2018, ArXiv.

[11]  Steven Bauer,et al.  Secure Data Deletion for Linux File Systems , 2001, USENIX Security Symposium.

[12]  Claudia Eckert,et al.  Is Feature Selection Secure against Training Data Poisoning? , 2015, ICML.

[13]  Danda B. Rawat,et al.  Cloud, Edge, and Fog Computing and Security for the Internet of Things , 2020 .

[14]  Ying-Chang Liang,et al.  Federated Learning in Mobile Edge Networks: A Comprehensive Survey , 2020, IEEE Communications Surveys & Tutorials.

[15]  Danda B. Rawat,et al.  Recent advances in mobile edge computing and content caching , 2020, Digit. Commun. Networks.

[16]  Salvatore J. Stolfo,et al.  Casting out Demons: Sanitizing Training Data for Anomaly Sensors , 2008, 2008 IEEE Symposium on Security and Privacy (sp 2008).

[17]  Xiaojin Zhu,et al.  Using Machine Teaching to Identify Optimal Training-Set Attacks on Machine Learners , 2015, AAAI.

[18]  Blaine Nelson,et al.  Poisoning Attacks against Support Vector Machines , 2012, ICML.

[19]  Blaine Nelson,et al.  The security of machine learning , 2010, Machine Learning.

[20]  Blaine Nelson,et al.  Exploiting Machine Learning to Subvert Your Spam Filter , 2008, LEET.

[21]  Fan Zhang,et al.  Stealing Machine Learning Models via Prediction APIs , 2016, USENIX Security Symposium.

[22]  Danda B. Rawat,et al.  Towards Federated Learning Approach to Determine Data Relevance in Big Data , 2019, 2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI).

[23]  Peter Gutmann,et al.  Secure deletion of data from magnetic and solid-state memory , 1996 .

[24]  Peter Richtárik,et al.  Federated Learning: Strategies for Improving Communication Efficiency , 2016, ArXiv.