Applying Differential Privacy Mechanism in Artificial Intelligence

Artificial Intelligence (AI) has attracted a large amount of attention in recent years. However, several new problems, such as privacy violations, security issues, or effectiveness, have been emerging. Differential privacy has several attractive properties that make it quite valuable for AI, such as privacy preservation, security, randomization, composition, and stability. Therefore, this paper presents differential privacy mechanisms for multi-agent systems, reinforcement learning, and knowledge transfer based on those properties, which proves that current AI can benefit from differential privacy mechanisms. In addition, the previous usage of differential privacy mechanisms in private machine learning, distributed machine learning, and fairness in models is discussed, bringing several possible avenues to use differential privacy mechanisms in AI. The purpose of this paper is to deliver the initial idea of how to integrate AI with differential privacy mechanisms and to explore more possibilities to improve AIs performance.

[1]  Qing-Long Han,et al.  A survey on recent advances in distributed sampled-data cooperative control of multi-agent systems , 2018, Neurocomputing.

[2]  Ameet Talwalkar,et al.  Federated Multi-Task Learning , 2017, NIPS.

[3]  Toniann Pitassi,et al.  Preserving Statistical Validity in Adaptive Data Analysis , 2014, STOC.

[4]  Anand D. Sarwate,et al.  Differentially Private Empirical Risk Minimization , 2009, J. Mach. Learn. Res..

[5]  Toniann Pitassi,et al.  Learning Fair Representations , 2013, ICML.

[6]  Ming Shao,et al.  Incomplete Multisource Transfer Learning , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[7]  Toniann Pitassi,et al.  Fairness through awareness , 2011, ITCS '12.

[8]  Katrina Ligett,et al.  A Simple and Practical Algorithm for Differentially Private Data Release , 2010, NIPS.

[9]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[10]  Alexandra Chouldechova,et al.  The Frontiers of Fairness in Machine Learning , 2018, ArXiv.

[11]  Kunal Talwar,et al.  Mechanism Design via Differential Privacy , 2007, 48th Annual IEEE Symposium on Foundations of Computer Science (FOCS'07).

[12]  Úlfar Erlingsson,et al.  RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response , 2014, CCS.

[13]  Ofra Amir,et al.  Interactive Teaching Strategies for Agent Training , 2016, IJCAI.

[14]  André Elisseeff,et al.  Stability and Generalization , 2002, J. Mach. Learn. Res..

[15]  Liming Chen,et al.  Discriminative Transfer Learning Using Similarities and Dissimilarities , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[16]  Saul Perlmutter,et al.  Blind analysis: Hide results to seek the truth , 2015, Nature.

[17]  Toniann Pitassi,et al.  The reusable holdout: Preserving validity in adaptive data analysis , 2015, Science.

[18]  Rui Zhang,et al.  A Hybrid Approach to Privacy-Preserving Federated Learning , 2018, Informatik Spektrum.

[19]  Matthew E. Taylor,et al.  Autonomously Reusing Knowledge in Multiagent Reinforcement Learning , 2018, IJCAI.

[20]  Frank McSherry,et al.  Privacy integrated queries: an extensible platform for privacy-preserving data analysis , 2009, SIGMOD Conference.

[21]  Franco Turini,et al.  k-NN as an implementation of situation testing for discrimination discovery and prevention , 2011, KDD.

[22]  Jonathan Ullman,et al.  Preventing False Discovery in Interactive Data Analysis Is Hard , 2014, 2014 IEEE 55th Annual Symposium on Foundations of Computer Science.

[23]  Philip S. Yu,et al.  Differentially Private Data Publishing and Analysis: A Survey , 2017, IEEE Transactions on Knowledge and Data Engineering.

[24]  Cynthia Dwork,et al.  Calibrating Noise to Sensitivity in Private Data Analysis , 2006, TCC.

[25]  Prateek Mittal,et al.  Analyzing Federated Learning through an Adversarial Lens , 2018, ICML.

[26]  Tassilo Klein,et al.  Differentially Private Federated Learning: A Client Level Perspective , 2017, ArXiv.

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