Watchdog: Detecting Ultrasonic-Based Inaudible Voice Attacks to Smart Home Systems

Mao, Jian; Zhu, Shishi; Dai, Xuan; Lin, Qixiao; Liu, Jian‐Wei

doi:10.1109/jiot.2020.2997779

Cited by 30 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where IðV ; YÞ and IðV ; ZÞ are the mutual information of an auxiliary random variable, V, and the received variable at Bob, Y, or the received variable at Eve, Z, when sending X at Alice, respectively. For a given channel, finding the secrecy capacity is equivalent to finding the joint distribution of V and X, i.e., pðv, xÞ, u ∈ U, x ∈ X, which maximizes the difference in (2). As the result, the secrecy capacity for an average power constraint can be calculated as follows:…”

Section: Secrecy Capacity (Sc)mentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Cooperative Jamming‐Based Secure Transmission for Energy‐Limited Systems

Huo

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Considering the ongoing development of various devices and rich applications in intelligent Internet of Things (IoT) systems, it is a crucial issue to solve secure transmission of legitimate signals for massive data sharing in the systems. Cooperative jamming-based physical layer security is explored to be a complement of conventional cryptographic schemes to protect private information. Yet, this method needs to solve a game between energy consumption and signal secure transmission. In this paper, we summarize the basics of cooperative jamming and universal security metrics. Using the metrics, we study a series of typical cooperative jamming strategies from two aspects, including power allocation and energy harvesting. Finally, we propose open issues and challenges of further works on cooperative jamming in an IoT system with energy constraints.

show abstract

Section: Secrecy Capacity (Sc)mentioning

confidence: 99%

“…Wiretap, caused by an eavesdropper, is a passive attack and does not interfere with legitimate transceivers. Though a legitimate receiver can receive untampered signals, the privacy leakage of these signals is unacceptable along with more attention to information security [2][3][4].…”

Section: Introductionmentioning

confidence: 99%

A Survey of Cooperative Jamming‐Based Secure Transmission for Energy‐Limited Systems

Huo

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…The main motivation of this research is the simplicity and purpose of adopting such features to the residence to convert the normal home into a wireless smart home. A wireless remote operation is enabled via any smart phone/tablet/Personal Computer (PC) /laptop equipped with the Android operating system [7,8], via a Graphical User Interface (GUI) based on the touch sensitive interface as well as voice assistance. This paper provides an option to customize the device according to the user end, with respect to self-configure and remote assistance-based controlling.…”

Section: *Author For Correspondencementioning

confidence: 99%

“…Mao et al, [8] proposed a paper related to the identification of ultrasonic sensor-enabled inaudible speech threats on smart home automation schemes. In this paper, the authors emphasize IoT as a vital foundation element and its operational capabilities for the rapidly growing cross-region, intelligent application and diverse cooperative smart building solutions that demand structured collaboration between numerous smart city technologies.…”

Section: Literature Reviewmentioning

confidence: 99%

ILeHCSA: an internet of things enabled smart home automation scheme with speech enabled controlling options using machine learning strategy

2021

IJATEE

View full text Add to dashboard Cite

show abstract

“…Also, some work has studied countermeasure techniques for improving the resilience of these system against adversarial attacks [19], [67], [88]. Most of these techniques are passive in nature, such as on the case of promoting the detection of an adversarial attack occurrence.…”

Section: Adversarial Attacks On Speech Recognition Systemsmentioning

confidence: 99%

Audio Attacks and Defenses against AED Systems -- A Practical Study

Santos¹,

Nilizadeh²

2021

Preprint

View full text Add to dashboard Cite

Audio Event Detection (AED) Systems capture audio from the environment and employ some deep learning algorithms for detecting the presence of a specific sound of interest. In this paper, we evaluate deep learning-based AED systems against evasion attacks through adversarial examples. We run multiple security critical AED tasks, implemented as CNNs classifiers, and then generate audio adversarial examples using two different types of noise, namely background and white noise, that can be used by the adversary to evade detection. We also examine the robustness of existing third-party AED capable devices, such as Nest devices manufactured by Google, which run their own black-box deep learning models.We show that an adversary can focus on audio adversarial inputs to cause AED systems to misclassify, similarly to what has been previously done by works focusing on adversarial examples from the image domain. We then, seek to improve classifiers' robustness through countermeasures to the attacks. We employ adversarial training and a custom denoising technique. We show that these countermeasures, when applied to audio input, can be successful, either in isolation or in combination, generating relevant increases of nearly fifty percent in the performance of the classifiers when these are under attack.

show abstract

Watchdog: Detecting Ultrasonic-Based Inaudible Voice Attacks to Smart Home Systems

Cited by 30 publications

References 26 publications

A Survey of Cooperative Jamming‐Based Secure Transmission for Energy‐Limited Systems

A Survey of Cooperative Jamming‐Based Secure Transmission for Energy‐Limited Systems

ILeHCSA: an internet of things enabled smart home automation scheme with speech enabled controlling options using machine learning strategy

Audio Attacks and Defenses against AED Systems -- A Practical Study

Contact Info

Product

Resources

About