Defeating hidden audio channel attacks on voice assistants via audio-induced surface vibrations

Wang, Chen; Anand, S.; Liu, Jian; Walker, Payton; Chen, Yingying; Saxena, Nitesh

doi:10.1145/3359789.3359830

Cited by 25 publications

(17 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al [34] proposed a novel approach that uses low-cost motion sensors to detect hidden voice commands against voice assistants. The authors leveraged audio and vibrant features to generate unique signatures, which can be easily deployed on smartphones with onboard motion sensors.…”

Section: Covert Channelmentioning

confidence: 99%

“…Furthermore, devices should be protected against the leakage of sensitive information to prevent sensor information abuse [98,99]. As some sensors can gather acoustic signals that humans cannot hear, an attacker can inject malicious commands with hidden voice commands [33,34]. To defend against such attacks, vendors should filter unnecessary audio channels in advance.…”

Section: Perception Layermentioning

confidence: 99%

“…In the perception layer, attackers try to steal information or send malicious commands through various covert channels. An adversary could remotely receive data by changing the lightness of smart lights [32], monitoring covert acoustic channels [77,78], and utilizing hidden voice methods to inject malicious commands [33,34]. Researchers have also tried to mitigate information leakage problems by optimizing the design variables and machine process [97].…”

Section: Attackmentioning

confidence: 99%

See 2 more Smart Citations

A Survey on Recent Advanced Research of CPS Security

et al. 2021

View full text Add to dashboard Cite

Cyber-physical systems (CPSs) are next-generation intelligent systems that integrate computing, communication, and control. Malicious attacks on CPSs can lead to both property damage and casualties. Therefore, it is worth surveying CPS security by reviewing and analyzing the latest high-quality related works. In this paper, we provide an overview of the CPS security studies from the last five years and select 142 related works from A- or B-level conferences/journals recommended by the China Computer Federation (CCF). First, we review the main contents of the selected papers and classify them into 24 topics. Then, we analyze hotspots and trends of CPS security technologies in three dimensions: (1) architecture layers (perception, network, and application); (2) application scenarios (smart grids, health care, smart transportation, smart homes, and general grids); and (3) MADC (Measure, Attack, Defense, and Control) types. Finally, we also perform a statistical analysis in terms of paper publication times, author institutes, countries, and sponsors to show the current worldwide CPS security research situation.

show abstract

Section: Covert Channelmentioning

confidence: 99%

Section: Perception Layermentioning

confidence: 99%

Section: Attackmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Recent Advanced Research of CPS Security

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Current defenses leverage this observation and employ mechanisms to detect the digital attack artifacts in the input signal [48,64,65]. These defenses target either the (1) physical properties of the speaker e.g.…”

Section: Introductionmentioning

confidence: 99%

Pipe Overflow: Smashing Voice Authentication for Fun and Profit

Ahmed¹,

Wani²,

Shamsabadi³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent years have seen a surge of popularity of acoustics-enabled personal devices powered by machine learning. Yet, machine learning has proven to be vulnerable to adversarial examples. Large number of modern systems protect themselves against such attacks by targeting the artificiality, i.e., they deploy mechanisms to detect the lack of human involvement in generating the adversarial examples. However, these defenses implicitly assume that humans are incapable of producing meaningful and targeted adversarial examples. In this paper, we show that this base assumption is wrong. In particular, we demonstrate that for tasks like speaker identification, a human is capable of producing analog adversarial examples directly with little cost and supervision: by simply speaking through a tube, an adversary reliably impersonates other speakers in eyes of ML models for speaker identification. Our findings extend to a range of other acoustic-biometric tasks such as liveness, bringing into question their use in security-critical settings in real life, such as phone banking.

show abstract

“…Existing Solutions. Existing authentication and defense mechanisms for VA systems relying on voice biometric technologies [3,22,26,39,44,46] use users' unique sound characteristics and machine learning-based models for user authentication. These solutions solely rely on acoustic features in the audio domain (i.e., extracting information from the data captured by microphones).…”

Section: Introductionmentioning

confidence: 99%