FakeWake: Understanding and Mitigating Fake Wake-up Words of Voice Assistants

Chen, Yanjiao; Bai, Yijie; Mitev, Richard; Wang, Kaibo; Sadeghi, Ahmad‐Reza; Xu, Wenyuan

doi:10.1145/3460120.3485365

Cited by 18 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other corpora exist with transcript ground-truth, typically to train voicerecognition systems, e.g., Common Voice (Ardila et al 2020) and Artie Bias (Meyer et al 2020), but they are not suitable to study transcription bias due to the short sentences and the likelihood that they have been already used to train those systems. (2020); Buolamwini and Gebru (2018)), where face recognition bias is evaluated for several personal characteristics; smart speakers wake-word recognition (e.g., Chen et al (2021); Dubois et al (2020)), where the authors show that certain categories of people are more likely to misactivate popular smart speakers; automated speaker recognition (Hutiri and Ding 2022;Fenu et al 2021;Meng et al 2022;Hajavi and Etemad 2023), where the authors analyze the fairness in recognizing speakers.…”

Section: Related Workmentioning

confidence: 99%

Fair or Fare? Understanding Automated Transcription Error Bias in Social Media and Videoconferencing Platforms

Dubois,

Holliday,

Waddell

et al. 2024

ICWSM

View full text Add to dashboard Cite

As remote work and learning increases in popularity, individuals, especially those with hearing impairments or who speak English as a second language, may depend on automated transcriptions to participate in business, school, entertainment, or basic communication. In this work, we investigate the automated transcription accuracy of seven popular social media and videoconferencing platforms with respect to some personal characteristics of their users, including gender, age, race, first language, speech rate, F0 frequency, and speech readability. We performed this investigation on a new corpus of 194 hours of English monologues by 846 TED talk speakers. Our results show the presence of significant bias, with transcripts less accurate for speakers that are male or non-native English speakers. We also observe differences in accuracy among platforms for different types of speakers. These results indicate that, while platforms have improved their automatic captioning, much work remains to make captions accessible for a wider variety of speakers and listeners.

show abstract

Section: Related Workmentioning

confidence: 99%

Fair or Fare? Understanding Automated Transcription Error Bias in Social Media and Videoconferencing Platforms

Dubois,

Holliday,

Waddell

et al. 2024

ICWSM

View full text Add to dashboard Cite

show abstract

“…We also identified 17 cases where the intended stakeholder was left unspecified [1], [4], [14], [19], [26], [32], [34]- [36], [39], [49], [59], [74], [76], [83], [115], [131]. These methods appear to heavily focus on the fidelity of the explanations instead of their understandability, removing the human from the loop and potentially limiting their deployability.…”

Section: The Importance Of Stakeholder Specificationmentioning

confidence: 99%

“…By visualizing the internal components of black-box models, malware analysts can identify sources of bias and misclassifications. Another example is from the domain of voice assistants: Chen et al [34] design a more robust voice assistant by first using SHAP to identify the type of fuzzy words that cause a given tree ensemble-based wake-up word detector to become falsely triggered, and then proposing countermeasures to avoid it from happening. Within continual learning settings, CADE [138] explains the cause of performance degradation of a malware detector by reporting the features that are most affected by concept drift.…”

Section: Xai-enabled Model Verificationmentioning

confidence: 99%

SoK: Explainable Machine Learning for Computer Security Applications

Nadeem,

Vos,

Cao

et al. 2023

2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P)

View full text Add to dashboard Cite

Explainable Artificial Intelligence (XAI) aims to improve the transparency of machine learning (ML) pipelines. We systematize the increasingly growing (but fragmented) microcosm of studies that develop and utilize XAI methods for defensive and offensive cybersecurity tasks. We identify 3 cybersecurity stakeholders, i.e., model users, designers, and adversaries, who utilize XAI for 4 distinct objectives within an ML pipeline, namely 1) XAI-enabled user assistance, 2) XAI-enabled model verification, 3) explanation verification & robustness, and 4) offensive use of explanations. Our analysis of the literature indicates that many of the XAI applications are designed with little understanding of how they might be integrated into analyst workflowsuser studies for explanation evaluation are conducted in only 14% of the cases. The security literature sometimes also fails to disentangle the role of the various stakeholders, e.g., by providing explanations to model users and designers while also exposing them to adversaries. Additionally, the role of model designers is particularly minimized in the security literature. To this end, we present an illustrative tutorial for model designers, demonstrating how XAI can help with model verification. We also discuss scenarios where interpretability by design may be a better alternative. The systematization and the tutorial enable us to challenge several assumptions, and present open problems that can help shape the future of XAI research within cybersecurity.

show abstract

“…There has been an increasing number of studies on VPA security and privacy [33,37,57,58]. The majority of research efforts have been undertaken to identify various acoustic-based attacks (e.g., out-of-band signal attacks and adversarial example attacks) against the Automatic Speech Recognition (ASR) modules in VPA systems [25,29,30,58] and the corresponding defenses in mitigating these attacks [26,31,47,61]. As hundreds of thousands of skills have been published in VPA platforms, the security of skills has attracted attention from the research community.…”

Section: Related Workmentioning

confidence: 99%

SkillScanner: Detecting Policy-Violating Voice Applications Through Static Analysis at the Development Phase

Liao,

Cheng,

Cai

et al. 2023

Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security

View full text Add to dashboard Cite

The Amazon Alexa marketplace is the largest Voice Personal Assistant (VPA) platform with over 100,000 voice applications (i.e., skills) published to the skills store. In an effort to maintain the quality and trustworthiness of voice-apps, Amazon Alexa has implemented a set of policy requirements to be adhered to by third-party skill developers. However, recent works reveal the prevalence of policyviolating skills in the current skills store. To understand the causes of policy violations in skills, we first conduct a user study with 34 third-party skill developers focusing on whether they are aware of the various policy requirements defined by the Amazon Alexa platform. Our user study results show that there is a notable gap between VPA's policy requirements and skill developers' practices. As a result, it is inevitable that policy-violating skills will be published.To prevent the inflow of new policy-breaking skills to the skills store from the source, it is critical to identify potential policy violations at the development phase. In this work, we design and develop SkillScanner, an efficient static code analysis tool to facilitate third-party developers to detect policy violations early in the skill development lifecycle. To evaluate the performance of SkillScanner, we conducted an empirical study on 2,451 open source skills collected from GitHub. SkillScanner effectively identified 1,328 different policy violations from 786 skills. Our results suggest that 32% of these policy violations are introduced through code duplication (i.e., code copy and paste). In particular, we found that 42 skill code examples from potential Alexa's official accounts (e.g., "alexa" and "alexa-samples" on GitHub) contain policy violations, which lead to 81 policy violations in other skills due to the copy-pasted code snippets from these Alexa's code examples. CCS CONCEPTS• Software and its engineering → Automated static analysis; • Security and privacy → Privacy protections.

show abstract

FakeWake: Understanding and Mitigating Fake Wake-up Words of Voice Assistants

Cited by 18 publications

References 23 publications

Fair or Fare? Understanding Automated Transcription Error Bias in Social Media and Videoconferencing Platforms

Fair or Fare? Understanding Automated Transcription Error Bias in Social Media and Videoconferencing Platforms

SoK: Explainable Machine Learning for Computer Security Applications

SkillScanner: Detecting Policy-Violating Voice Applications Through Static Analysis at the Development Phase

Contact Info

Product

Resources

About