Adversarial Transferability in Embedded Sensor Systems: An Activity Recognition Perspective Article Swipe

MAKE IMPACT

Ramesh Kumar Sah , Hassan Ghasemzadeh · YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.1145/3641861

Machine learning algorithms are increasingly used for inference and decision-making in embedded systems. Data from sensors are used to train machine learning models for various smart functions of embedded and cyber-physical systems ranging from applications in healthcare, autonomous vehicles, and national security. However, recent studies have shown that machine learning models can be fooled by adding adversarial noise to their inputs. The perturbed inputs are called adversarial examples. Furthermore, adversarial examples designed to fool one machine learning system are also often effective against another system. This property of adversarial examples is called adversarial transferability and has not been explored in wearable systems to date. In this work, we take the first stride in studying adversarial transferability in wearable sensor systems from four viewpoints: (1) transferability between machine learning models; (2) transferability across users/subjects of the embedded system; (3) transferability across sensor body locations; and (4) transferability across datasets used for model training. We present a set of carefully designed experiments to investigate these transferability scenarios. We also propose a threat model describing the interactions of an adversary with the source and target sensor systems in different transferability settings. In most cases, we found high untargeted transferability, whereas targeted transferability success scores varied from 0% to 80%. The transferability of adversarial examples depends on many factors such as the inclusion of data from all subjects, sensor body position, number of samples in the dataset, type of learning algorithm, and the distribution of source and target system dataset. The transferability of adversarial examples decreased sharply when the data distribution of the source and target system became more distinct. We also provide guidelines and suggestions for the community for designing robust sensor systems. Code and dataset used in our analysis is publicly available here. 1

Type

article

Language

en

Landing Page

https://doi.org/10.1145/3641861

PDF

https://dl.acm.org/doi/pdf/10.1145/3641861

OA Status

hybrid

Cited By

2

References

30

Related Works

10

OpenAlex ID

https://openalex.org/W4391103909

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4391103909

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.1145/3641861

Digital Object Identifier

Title

Adversarial Transferability in Embedded Sensor Systems: An Activity Recognition Perspective

Work title

Type

article

OpenAlex work type

Language

en

Primary language

Publication year

2024

Year of publication

Publication date

2024-01-22

Full publication date if available

Authors

Ramesh Kumar Sah, Hassan Ghasemzadeh

List of authors in order

Landing page

https://doi.org/10.1145/3641861

Publisher landing page

PDF URL

https://dl.acm.org/doi/pdf/10.1145/3641861

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

hybrid

Open access status per OpenAlex

OA URL

https://dl.acm.org/doi/pdf/10.1145/3641861

Direct OA link when available

Concepts

Transferability, Computer science, Adversarial system, Wearable computer, Machine learning, Artificial intelligence, Embedded system, Logit

Top concepts (fields/topics) attached by OpenAlex

Cited by

2

Total citation count in OpenAlex

Citations by year (recent)

2025: 1, 2024: 1

Per-year citation counts (last 5 years)

References (count)

30

Number of works referenced by this work

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload