A Multiversion Programming Inspired Approach to Detecting Audio Adversarial Examples

Zeng, Qiang; Su, Jianhai; Fu, Chenglong; Kayas, Golam; Luo, Lannan

doi:10.48550/arxiv.1812.10199

Cited by 3 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) The privacy of smart home Although manufacturers have deployed various measurements of their platforms, some papers still found flaws leaking users' privacy on various platforms [28]- [31]. There have been many papers showing how to compromise a user's privacy via the flaws of cloud [32]- [35], protocols, voice interface [36], or even traffic analysis. Yoshigoe et al proposed the Synthetic Packet Injection to hide the real traffic between devices and the cloud [37].…”

Section: ) Iot Securitymentioning

confidence: 99%

Privacy Leakage in Smart Homes and Its Mitigation: IFTTT as a Case Study

Zeng

Zhu

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

The combination of smart home platforms and automation apps introduces much convenience to smart home users. However, this also brings the potential for privacy leakage. If a smart home platform is permitted to collect all the events of a user day and night, then the platform will learn the behavior patterns of this user before long. In this paper, we investigate how IFTTT, one of the most popular smart home platforms, has the capability of monitoring the daily life of a user in a variety of ways that are hardly noticeable. Moreover, we propose multiple ideas for mitigating privacy leakages, which altogether forms a "Filter-and-Fuzz" (F&F) process: first, it filters out events unneeded by the IFTTT platform; then, it fuzzes the values and frequencies of the remaining events. We evaluate the F&F process, and the results show that the proposed solution makes IFTTT unable to recognize any of the user's behavior patterns. INDEX TERMS IFTTT, privacy leakage, smart home, SmartThings I. INTRODUCTION

show abstract

Section: ) Iot Securitymentioning

confidence: 99%

Privacy Leakage in Smart Homes and Its Mitigation: IFTTT as a Case Study

Zeng

Zhu

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, a lexicon and language model is applied to obtain the recognition result "open". When Several works have been proposed to detect and defend such adversarial attacks [3,4,10]. Zeng et al leveraged multiple Automatic Speech Recognition (ASR) systems to detect audio physical adversarial attack based on a cross-verification methodology [4].…”

Section: Audio Physical Adversarial Attack Defensementioning

confidence: 99%

“…When Several works have been proposed to detect and defend such adversarial attacks [3,4,10]. Zeng et al leveraged multiple Automatic Speech Recognition (ASR) systems to detect audio physical adversarial attack based on a cross-verification methodology [4]. However, their method lacks certain versatility which cannot detect the adversarial attacks with model transferability.…”

Section: Audio Physical Adversarial Attack Defensementioning

confidence: 99%

“…Many works have been proposed to defend against physical adversarial attacks [1][2][3][4]. However, most of them neglected CNN's intrinsic vulnerability interpretations.…”

Section: Introductionmentioning

confidence: 99%

“…However, most of them neglected CNN's intrinsic vulnerability interpretations. Instead, either they merely focused on eliminating explicit perturbation patterns from input [2], or they simply adopted multiple CNNs to conduct the cross-verification [3,4]. All these methods have certain drawbacks: They failed to find a common defense methodology, lacking versatility for preventing different physical adversarial attacks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

LanCe: A Comprehensive and Lightweight CNN Defense Methodology against Physical Adversarial Attacks on Embedded Multimedia Applications

Xu¹,

Yu²,

Chen³

2019

Preprint

View full text Add to dashboard Cite

Recently, adversarial attacks can be applied to the physical world, causing practical issues to various Convolutional Neural Networks (CNNs) powered applications. Most existing physical adversarial attack defense works only focus on eliminating explicit perturbation patterns from inputs, ignoring interpretation to CNN's intrinsic vulnerability. Therefore, they lack expected versatility to different attacks and thereby depend on considerable data processing costs. In this paper, we propose LanCe -a comprehensive and lightweight CNN defense methodology against different physical adversarial attacks. By interpreting CNN's vulnerability, we find that non-semantic adversarial perturbations can activate CNN with significantly abnormal activations and even overwhelm other semantic input patterns' activations. We improve the CNN recognition process by adding a self-verification stage to detect the potential adversarial input with only one CNN inference cost. Based on the detection result, we further propose a data recovery methodology to defend the physical adversarial attacks. We apply such defense methodology into both image and audio CNN recognition scenarios and analyze the computational complexity for each scenario, respectively. Experiments show that our methodology can achieve an average 91% successful rate for attack detection and 89% accuracy recovery. Moreover, it is at most 3× faster compared with the state-of-the-art defense methods, making it feasible to resource-constrained embedded systems, such as mobile devices.

show abstract