Adversarial Attacks on Machine Learning in Embedded and IoT Platforms
Not on the map. Why?
Abstract (arXiv)
Machine learning (ML) algorithms are increasingly being integrated into embedded and IoT systems that surround us, and they are vulnerable to adversarial attacks. The deployment of these ML algorithms on resource-limited embedded platforms also requires the use of model compression techniques. The impact of such model compression techniques on adversarial robustness in ML is an important and emerging area of research. This article provides an overview of the landscape of adversarial attacks and ML model compression techniques relevant to embedded systems. We then describe efforts that seek to understand the relationship between adversarial attacks and ML model compression before discussing open problems in this area.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 31 references that are in the map. First posted on arXiv 3 Mar 2023.
Builds on
22 of 31 references.
References · 22
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2013Intriguing properties of neural networkscited by 5,155
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
- 2016Adversarial examples in the physical worldcited by 1,769
- 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
- 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
- 2021Scaling Vision Transformerscited by 999
- 2016Practical Black-Box Attacks against Machine Learningcited by 903
- 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
- 2016Stealing Machine Learning Models via Prediction APIscited by 619
- 2018Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networkscited by 580
10 more
- 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 446
- 2018Adversarial Attacks and Defences: A Surveycited by 259
- 2017Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimizationcited by 197
- 2019Defensive Quantization: When Efficiency Meets Robustnesscited by 95
- 2020Methods for Pruning Deep Neural Networkscited by 49
- 2020A Survey on Deep Neural Network Compression: Challenges, Overview, and Solutionscited by 32
- 2017Attacking Binarized Neural Networkscited by 29
- 2021CHISEL: Compression-Aware High-Accuracy Embedded Indoor Localization with Deep Learningcited by 10
- 2019Impact of Low-bitwidth Quantization on the Adversarial Robustness for Embedded Neural Networkscited by 9
- 2021A Layer-wise Adversarial-aware Quantization Optimization for Improving Robustnesscited by 3
Built on by
Citing papers per year: 2023: 1.
1 paper.