Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey

Abstract

Deep Neural Network (DNN), one of the most powerful machine learning algorithms, is increasingly leveraged to overcome the bottleneck of effectively exploring and analyzing massive data to boost advanced scientific development. It is not a surprise that cloud computing providers offer the cloud-based DNN as an out-of-the-box service. Though there are some benefits from the cloud-based DNN, the interaction mechanism among two or multiple entities in the cloud inevitably induces new privacy risks. This survey presents the most recent findings of privacy attacks and defenses appeared in cloud-based neural network services. We systematically and thoroughly review privacy attacks and defenses in the pipeline of cloud-based DNN service, i.e., data manipulation, training, and prediction. In particular, a new theory, called cloud-based ML privacy game, is extracted from the recently published literature to provide a deep understanding of state-of-the-art research. Finally, the challenges and future work are presented to help researchers to continue to push forward the competitions between privacy attackers and defenders.

References in corpus (30)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Explaining and Harnessing Adversarial Examples
• A Unified Approach to Interpreting Model Predictions
• Deep Learning with Differential Privacy
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• DeepPose: Human Pose Estimation via Deep Neural Networks
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Understanding deep learning requires rethinking generalization
• Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
• Provable defenses against adversarial examples via the convex outer adversarial polytope
• Adversarially Learned Inference
• On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
• A Survey of Privacy Attacks in Machine Learning
• Machine Learning Based Cyber Attacks Targeting on Controlled Information: A Survey
• AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning
• PowerSpy: Location Tracking using Mobile Device Power Analysis
• You are Who You Know and How You Behave: Attribute Inference Attacks via Users' Social Friends and Behaviors
• TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service
• DAWN: Dynamic Adversarial Watermarking of Neural Networks
• Boosting Privately: Privacy-Preserving Federated Extreme Boosting for Mobile Crowdsensing
• Entangled Watermarks as a Defense against Model Extraction
• Analyzing and Improving Representations with the Soft Nearest Neighbor Loss
• Information Leakage Games
• GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators
• Differential Privacy for the Analyst via Private Equilibrium Computation
• Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment
• An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks
• Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness