Ayomide Akinsanya (Stevens Institute of Technology), Tegan Brennan (Stevens Institute of Technology)

Current machine learning systems offer great predictive power but also require significant computational resources. As a result, the promise of a class of optimized machine learning models, called adaptive neural networks (ADNNs), has seen recent wide appeal. These models make dynamic decisions about the amount of computation to perform based on the given input, allowing for fast predictions on ”easy” input. While various considerations of ADNNs have been extensively researched, how these input-dependent optimizations might introduce vulnerabilities has been hitherto under-explored. Our work is the first to demonstrate and evaluate timing channels due to the optimizations of ADNNs with the capacity to leak sensitive attributes about a user’s input. We empirically study six ADNNs types and demonstrate how an attacker can significantly improve their ability to infer sensitive attributes, such as class label, of another user’s input from an observed timing measurement. Our results show that timing information can increase an attacker’s probability of correctly inferring the attribute of the user’s input by up to a factor of 9.89x. Our empirical evaluation uses four different datasets, including those containing sensitive medical and demographic information, and considers leakage across a variety of sensitive attributes of the user's input. We conclude by demonstrating how timing channels can be exploited across the public internet in two fictitious web applications — Fictitious Health Company and Fictitious HR — that makes use of ADNNs for serving predictions to their clients.

View More Papers

It’s Standards’ Time to Shine: Insights for IoT Cybersecurity...

Dr. Michael J. Fagan, National Institute of Standards and Technology

Read More

Securing the Satellite Software Stack

Samuel Jero (MIT Lincoln Laboratory), Juliana Furgala (MIT Lincoln Laboratory), Max A Heller (MIT Lincoln Laboratory), Benjamin Nahill (MIT Lincoln Laboratory), Samuel Mergendahl (MIT Lincoln Laboratory), Richard Skowyra (MIT Lincoln Laboratory)

Read More

Inaudible Adversarial Perturbation: Manipulating the Recognition of User Speech...

Xinfeng Li (Zhejiang University), Chen Yan (Zhejiang University), Xuancun Lu (Zhejiang University), Zihan Zeng (Zhejiang University), Xiaoyu Ji (Zhejiang University), Wenyuan Xu (Zhejiang University)

Read More

A Two-Layer Blockchain Sharding Protocol Leveraging Safety and Liveness...

Yibin Xu (University of Copenhagen), Jingyi Zheng (University of Copenhagen), Boris Düdder (University of Copenhagen), Tijs Slaats (University of Copenhagen), Yongluan Zhou (University of Copenhagen)

Read More