PriMask: Cascadable and Collusion-Resilient Data Masking for Mobile Cloud Inference
Mobile cloud offloading is indispensable for inference tasks based on large-scale deep models. However, transmitting privacy-rich inference data to the cloud incurs concerns. This paper presents the design of a system called PriMask, in which the mobile device uses a secret small-scale neural network called MaskNet to mask the data before transmission. PriMask significantly weakens the cloud's capability to recover the data or extract certain private attributes. The MaskNet is em cascadable in that the mobile can opt in to or out of its use seamlessly without any modifications to the cloud's inference service. Moreover, the mobiles use different MaskNets, such that the collusion between the cloud and some mobiles does not weaken the protection for other mobiles. We devise a {\em split adversarial learning} method to train a neural network that generates a new MaskNet quickly (within two seconds) at run time. We apply PriMask to three mobile sensing applications with diverse modalities and complexities, i.e., human activity recognition, urban environment crowdsensing, and driver behavior recognition. Results show PriMask's effectiveness in all three applications.
Code (1)
Tasks
Activity RecognitionHuman Activity RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Cascadable all-optical NAND gates using diffractive networks
Owing to its potential advantages such as scalability, low latency and power efficiency, optical computing has seen rapid advances over the last decades. A core unit of a potential all-optical processor would be the NAND…
AllOn Singleton Congestion Games with Resilience Against Collusion
We study the subclass of singleton congestion games with identical and increasing cost functions, i.e., each agent tries to utilize from the least crowded resource in her accessible subset of resources. Our main contribu…
Artificial Intelligence and Algorithmic Price Collusion in Two-sided Markets
Algorithmic price collusion facilitated by artificial intelligence (AI) algorithms raises significant concerns. We examine how AI agents using Q-learning engage in tacit collusion in two-sided markets. Our experiments re…
Q-LearningSoK: Colluding Adversaries in Machine Learning Pipelines
Machine learning (ML) models are susceptible to various security, privacy, and fairness risks. Adversaries with different characteristics (i.e., objectives, knowledge, and capabilities) can collude by executing one attac…
Tacit algorithmic collusion in deep reinforcement learning guided price competition: A study using EV charge pricing game
Players in pricing games with complex structures are increasingly adopting artificial intelligence (AI) aided learning algorithms to make pricing decisions for maximizing profits. This is raising concern for the antitrus…
Deep Reinforcement Learning