Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responses
Not on the map. Why?
Abstract (arXiv)
Keyless entry systems in cars are adopting neural networks for localizing its operators. Using test-time adversarial defences equip such systems with the ability to defend against adversarial attacks without prior training on adversarial samples. We propose a test-time adversarial example detector which detects the input adversarial example through quantifying the localized intermediate responses of a pre-trained neural network and confidence scores of an auxiliary softmax layer. Furthermore, in order to make the network robust, we extenuate the non-relevant features by non-iterative input sample clipping. Using our approach, mean performance over 15 levels of adversarial perturbations is increased by 55.33% for the fast gradient sign method (FGSM) and 6.3% for both the basic iterative method (BIM) and the projected gradient method (PGD).
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 28 references that are in the map. First posted on arXiv 10 Nov 2022.
Builds on
22 of 28 references.
References · 22
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2013Intriguing properties of neural networkscited by 5,155
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
- 2019Adversarial Training for Free!cited by 643
- 2022Diffusion Models for Adversarial Purificationcited by 476
- 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
- 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 278
- 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 246
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
- 2018Adversarial Logit Pairingcited by 224
- 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
10 more
- 2021Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attackscited by 91
- 2022Evaluating the Adversarial Robustness of Adaptive Test-time Defensescited by 64
- 2021Adversarial Attacks are Reversible with Natural Supervisioncited by 47
- 2021Attacking Adversarial Attacks as A Defensecited by 32
- 2021Combating Adversaries with Anti-Adversariescited by 27
- 2021Towards Robust Neural Networks via Close-loop Controlcited by 23
- 2021Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attackscited by 20
- 2021AID-Purifier: A Light Auxiliary Network for Boosting Adversarial Defensecited by 10
- 2021Ghost Peak: Practical Distance Reduction Attacks Against HRP UWB Rangingcited by 1
- 2022Evil Never Sleeps: When Wireless Malware Stays On After Turning Off iPhonescited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.