Automated Side Channel Analysis of Media Software with Manifold Learning

Abstract

The prosperous development of cloud computing and machine learning as a service has led to the widespread use of media software to process confidential media data. This paper explores an adversary's ability to launch side channel analyses (SCA) against media software to reconstruct confidential media inputs. Recent advances in representation learning and perceptual learning inspired us to consider the reconstruction of media inputs from side channel traces as a cross-modality manifold learning task that can be addressed in a unified manner with an autoencoder framework trained to learn the mapping between media inputs and side channel observations. We further enhance the autoencoder with attention to localize the program points that make the primary contribution to SCA, thus automatically pinpointing information-leakage points in media software. We also propose a novel and highly effective defensive technique called perception blinding that can perturb media inputs with perception masks and mitigate manifold learning-based SCA.Our evaluation exploits three popular media software to reconstruct inputs in image, audio, and text formats. We analyze three common side channels -cache bank, cache line, and page tables -and userspace-only cache set accesses logged by standard Prime+Probe. Our framework successfully reconstructs high-quality confidential inputs from the assessed media software and automatically pinpoint their vulnerable program points, many of which are unknown to the public. We further show that perception blinding can mitigate manifold learning-based SCA with negligible extra cost.

Layered Binary Templating: Efficient Detection of Compiler- and Linker-introduced Leakage

“…Li et al [59] demonstrated a neural network to perform power analysis attacks automatically. Yuan et al [116] demonstrated that manifold learning can be used to detect and locate side-channel leakage in media software.…”

“…Most of these works focus on cryptographic implementations and aim for the goal of making the code constant-time [19], [79], [63], [13]. More recently, Yuan et al [116] showed that manifold learning can be used for automated side-channel analysis of media software. For common applications processing sensitive input, e.g., browsers, the situation is less clear, as it is not feasible to linearize and unify the entire instruction stream for different user inputs that trigger vastly different program behavior.…”