Object detectors have many applications in safety-critical systems, but they are known to be sensitive to worst-case perturbations such as adversarial attacks, which limits their applicability in real-world scenarios. Compared with classification, adversarial robustness for object detection has received less attention, and existing methods are often tied to adversarial training, whose performance may not transfer across attacks, perturbation budgets, or architectures.
arXiv:2607. 06592v1 Announce Type: cross Abstract: Object detectors have many applications in safety-critical systems, but they are known to be sensitive to worst-case perturbations such as adversarial attacks, which limits their applicability in real-world scenarios.
Camera-based object detectors are vulnerable to physical adversarial attacks designed to suppress detections. While adversarial training and input purification offer some protection, they often overfit to specific attack distributions and fail on adaptive adversaries.
arXiv:2609.28239v1 Announce Type: new Abstract: With the development of applications like autonomous driving, object detection has gained significant attention, while also highlighting critical vulne...
arXiv:2608. 16031v1 Announce Type: new Abstract: Camera-based object detectors are vulnerable to physical adversarial attacks designed to suppress detections.
With the development of applications like autonomous driving, object detection has gained significant attention, while also highlighting critical vulnerabilities like backdoor attacks that severely co...
arXiv:2608.29510v1 Announce Type: cross Abstract: Aerial object detection is increasingly deployed in real-world applications, but models remain vulnerable to physical, universal adversarial patches...
While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks. Existing defense methods predominantly target single-task scenarios (e.
arXiv:2607. 18958v1 Announce Type: cross Abstract: While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks.
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.
arXiv:2608. 07750v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) have found successful deployment in numerous vision perception systems.
arXiv:2606. 02267v1 Announce Type: new Abstract: The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment.
Adversarial attacks pose a challenge to the reliability of deep learning models, motivating effective detection methods. Existing techniques often rely on attack-specific assumptions, access to adversarial samples, or knowledge of the underlying classifier (white-box).