Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Information

Abstract

Adversarial attacks against commercial black-box speech platforms, including cloud speech APIs and voice control devices, have received little attention until recent years. The current "black-box" attacks all heavily rely on the knowledge of prediction/confidence scores to craft effective adversarial examples, which can be intuitively defended by service providers without returning these messages. In this paper, we propose two novel adversarial attacks in more practical and rigorous scenarios. For commercial cloud speech APIs, we propose Occam, a decision-only black-box adversarial attack, where only final decisions are available to the adversary. In Occam, we formulate the decision-only AE generation as a discontinuous large-scale global optimization problem, and solve it by adaptively decomposing this complicated problem into a set of sub-problems and cooperatively optimizing each one. Our Occam is a one-size-fits-all approach, which achieves 100% success rates of attacks with an average SNR of 14.23dB, on a wide range of popular speech and speaker recognition APIs, including Google, Alibaba, Microsoft, Tencent, iFlytek, and Jingdong, outperforming the state-of-the-art black-box attacks. For commercial voice control devices, we propose NI-Occam, the first non-interactive physical adversarial attack, where the adversary does not need to query the oracle and has no access to its internal information and training data. We combine adversarial attacks with model inversion attacks, and thus generate the physically-effective audio AEs with high transferability without any interaction with target devices. Our experimental results show that NI-Occam can successfully fool Apple Siri, Microsoft Cortana, Google Assistant, iFlytek and Amazon Echo with an average SRoA of 52% and SNR of 9.65dB, shedding light on non-interactive physical attacks against voice control devices.

A version of this paper appears in the proceedings of the 28th ACM Conference on Computer and Communications Security (CCS 2021). The notes in Tables 1 and 4 have been updated

References in corpus (8)

• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques
• DolphinAtack: Inaudible Voice Commands
• Fast is better than free: Revisiting adversarial training
• Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
• Instance adaptive adversarial training: Improved accuracy tradeoffs in neural nets
• Adversarial Attack and Defense Strategies for Deep Speaker Recognition Systems
• Generalizing Adversarial Examples by AdaBelief Optimizer

Cited by in corpus (4)

• Multi-SpacePhish: Extending the Evasion-space of Adversarial Attacks against Phishing Website Detectors using Machine Learning
• VSMask: Defending Against Voice Synthesis Attack via Real-Time Predictive Perturbation
• SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems
• Compensating Removed Frequency Components: Thwarting Voice Spectrum Reduction Attacks