Cybersecurity of autonomous vehicles: A systematic literature review of adversarial attacks and defense models
Autonomous driving (AD) has developed tremendously in parallel with the ongoing
development and improvement of deep learning (DL) technology. However, the uptake of …
development and improvement of deep learning (DL) technology. However, the uptake of …
On the real-world adversarial robustness of real-time semantic segmentation models for autonomous driving
The existence of real-world adversarial examples (RWAEs)(commonly in the form of
patches) poses a serious threat for the use of deep learning models in safety-critical …
patches) poses a serious threat for the use of deep learning models in safety-critical …
Kaleidoscope: Physical backdoor attacks against deep neural networks with RGB filters
Recent research has shown that deep neural networks are vulnerable to backdoor attacks. A
carefully-designed backdoor trigger will mislead the victim model to misclassify any sample …
carefully-designed backdoor trigger will mislead the victim model to misclassify any sample …
Objectseeker: Certifiably robust object detection against patch hiding attacks via patch-agnostic masking
Object detectors, which are widely deployed in security-critical systems such as autonomous
vehicles, have been found vulnerable to patch hiding attacks. An attacker can use a single …
vehicles, have been found vulnerable to patch hiding attacks. An attacker can use a single …
Defending physical adversarial attack on object detection via adversarial patch-feature energy
Object detection plays an important role in security-critical systems such as autonomous
vehicles but has shown to be vulnerable to adversarial patch attacks. Existing defense …
vehicles but has shown to be vulnerable to adversarial patch attacks. Existing defense …
PAD: Patch-Agnostic Defense against Adversarial Patch Attacks
L Jing, R Wang, W Ren, X Dong… - Proceedings of the …, 2024 - openaccess.thecvf.com
Adversarial patch attacks present a significant threat to real-world object detectors due to
their practical feasibility. Existing defense methods which rely on attack data or prior …
their practical feasibility. Existing defense methods which rely on attack data or prior …
Defending person detection against adversarial patch attack by using universal defensive frame
Person detection has attracted great attention in the computer vision area and is an
imperative element in human-centric computer vision. Although the predictive performances …
imperative element in human-centric computer vision. Although the predictive performances …
Object Detectors in the Open Environment: Challenges, Solutions, and Outlook
With the emergence of foundation models, deep learning-based object detectors have
shown practical usability in closed set scenarios. However, for real-world tasks, object …
shown practical usability in closed set scenarios. However, for real-world tasks, object …
HARP: Let Object Detector Undergo Hyperplasia to Counter Adversarial Patches
J Cai, S Chen, H Li, B Xia, Z Mao, W Yuan - Proceedings of the 31st …, 2023 - dl.acm.org
Adversarial patches can mislead object detectors to produce erroneous predictions. To
defend against adversarial patches, one can take two types of protections on the model side …
defend against adversarial patches, one can take two types of protections on the model side …
Defending from physically-realizable adversarial attacks through internal over-activation analysis
This work presents Z-Mask, an effective and deterministic strategy to improve the adversarial
robustness of convolutional networks against physically-realizable adversarial attacks. The …
robustness of convolutional networks against physically-realizable adversarial attacks. The …