Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems

Ozbulak, Utku; Vandersmissen, Baptist; Jalalvand, Azarakhsh; Couckuyt, Ivo; Messem, Arnout Van; Neve, Wesley De

doi:10.1016/j.cviu.2020.103111

Cited by 12 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data security has been addressed through local training via federated architecture, preventing data from being sent to third parties [99]. Detection of spoofing attacks in video replay and vulnerability to adversarial attacks in video and radar data have also been investigated [100,101].…”

Section: Privacymentioning

confidence: 99%

Human Action Recognition in Smart Living Services and Applications: Context Awareness, Data Availability, Personalization, and Privacy

Diraco¹,

Rescio²,

Caroppo³

et al. 2023

Preprint

View full text Add to dashboard Cite

Smart Living, an increasingly prominent concept, entails incorporating sophisticated technologies in homes and urban environments to elevate the quality of life for citizens. A critical success factor for Smart Living services and applications, from energy management to healthcare and transportation, is the efficacy of human action recognition (HAR). HAR, rooted in computer vision, seeks to identify human actions and activities using visual data and various sensor modalities. This paper extensively reviews the literature on HAR in Smart Living services and applications, amalgamating key contributions and challenges while providing insights into future research directions. The review delves into the essential aspects of Smart Living, the state of the art in HAR, and the potential societal implications of this technology. Moreover, the paper meticulously examines the primary application sectors in Smart Living that stand to gain from HAR, such as smart homes, smart healthcare, and smart cities. By underscoring the significance of the four dimensions of Context Awareness, Data Availability, Personalization, and Privacy in HAR, this paper serves as a valuable resource for researchers and practitioners striving to advance Smart Living services and applications.

show abstract

Section: Privacymentioning

confidence: 99%

Human Action Recognition in Smart Living Services and Applications: Context Awareness, Data Availability, Personalization, and Privacy

Diraco¹,

Rescio²,

Caroppo³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…To develop the universal and targeted adversarial attack against such HAR system, several challenges should be solved: (1) Rather than an untargeted attack aimed at disabling the HAR system, our attack should employ more complex adversarial learning processes to make the adversarial mmWave data be recognized as the adversary-desired activity; (2) The difference between the produced adversarial sample and the original mmWave data representation should be as little as possible, making the activity data stealthy and unnoticeable to bare human eyes; (3) In order to make the attack be launched in practice, the method should produce adversarial samples within a short latency that the targeted attack is ready to be launched without any additional computation.…”

Section: Challengesmentioning

confidence: 99%

“…More recently, researchers explores the vulnerability of adversarial attacks in mmWave-based HAR systems. However, they only investigate the feasibility of making the HAR systems output incorrect labels [2]. How to make the HAR systems output desired labels still remains unexplored.…”

Section: Introductionmentioning

confidence: 99%

Universal targeted attacks against mmWave-based human activity recognition system

Xie

Jiang

Guo

et al. 2022

Proceedings of the 20th Annual International Conference on Mobile Systems, Applications and Services

View full text Add to dashboard Cite

Millimeter wave (mmWave)-based human activity recognition (HAR) systems have emerged in recent years due to their better privacy preservation and higher-resolution sensing. However, these systems are vulnerable to adversarial attacks. In this work, we propose a universal targeted attack method for mmWave-based HAR system. In particular, a universal perturbation is generated in advance which can be added to new-coming mmWave data to deceive the HAR system, causing it to output our desired label. We validate our proposed attack using a public mmWave dataset. We demonstrate the effectiveness of our proposed universal attack with a high attack success rate of over 95%. CCS CONCEPTS• Security and privacy → Mobile and wireless security; • Human-centered computing → Ubiquitous and mobile computing systems and tools; • Computing methodologies → Machine learning.

show abstract

“…In the radar domain, research has not progressed that far, and in addition, preprocessing of radar data complicates attack methodologies. Thus, there is some work in the radar adversarial attack area, but their commonality is the limitation to attack scenarios on already preprocessed and recorded data [21]. This means that the radar-specific signal shape is not taken into account, but the problem is transformed into a visual representation and attacked with successful algorithms from the visual domain.…”

Section: Adversarial Attacksmentioning

confidence: 99%

Universal Adversarial Attacks on the Raw Data From a Frequency Modulated Continuous Wave Radar

Valtl

Issakov

2022

IEEE Access

View full text Add to dashboard Cite

This work is a result of a collaboration between the projects "KI-Flex" (project number 16ES1027), funded by the German Federal Ministry of Education and Research (BMBF) within the founding program Microelectronic from Germany innovation driver, the "KoSi" project, (project number 01MM20011C) funded by the German Federal Ministry for Digital and Transport (BMDV) within the funding program "Automatisiertes, Vernetztes Fahren" and the project "TEACHING" (project number 871385) founded by the Horizon 2020 program."ABSTRACT As more and more applications rely on Artificial Intelligence (AI), it is inevitable to explore the associated safety and security risks, especially for sensitive applications where physical integrity is at risk. One of the most interesting challenges that come with AI are adversarial attacks being a wellresearched problem in the visual domain, where a small change in the input data can cause the Neural Network (NN) to make an incorrect prediction. In the radar domain, AI is not that widespread yet but the results that AI applications produce are very promising, which is why more and more applications based on it are being used. This work presents three possible attack methods that are particularly suitable for the radar domain. The developed algorithms generate universal adversarial attack patches for all sorts of radar applications based on NN. The main goal of the algorithms, apart from the computation of universal patches, is the identification of sensitive areas in the raw radar data input which than can be examined more closely. To the best of our knowledge, this is the first work that deals with calculating universal patches on raw radar data, which is of great importance especially for interference analysis. The developed algorithms have been verified on two data sets. One in the field of autonomous driving where the attacks lead to a steering misprediction of up to 0.3 for the steering value which is within [-1,1], with the results also being successfully tested on a demonstrator. The other data set originated from a gesture recognition task, where the attacks decreased the accuracy, originally at 97.0% up to a minimum of 16.5%, which is slightly above 12.5% being the accuracy for a purely random prediction.INDEX TERMS adversarial attacks, artificial neural networks, autonomous vehicles, edge computing, object recognition, radar applications, real-time systems

show abstract

Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems

Cited by 12 publications

References 40 publications

Human Action Recognition in Smart Living Services and Applications: Context Awareness, Data Availability, Personalization, and Privacy

Human Action Recognition in Smart Living Services and Applications: Context Awareness, Data Availability, Personalization, and Privacy

Universal targeted attacks against mmWave-based human activity recognition system

Universal Adversarial Attacks on the Raw Data From a Frequency Modulated Continuous Wave Radar

Contact Info

Product

Resources

About