Adversarial Camera Patch: An Effective and Robust Physical-World Attack on Object Detectors
This addresses the issue of stealthiness in adversarial attacks for security applications, but it appears incremental as it builds on existing camera-based methods.
The paper tackles the problem of making physical-world attacks on object detectors more stealthy by proposing an Adversarial Camera Patch (ADCP) that uses a single patch on the camera lens to introduce perturbations, avoiding the need for multiple patches and reducing complexity.
Nowadays, the susceptibility of deep neural networks (DNNs) has garnered significant attention. Researchers are exploring patch-based physical attacks, yet traditional approaches, while effective, often result in conspicuous patches covering target objects. This leads to easy detection by human observers. Recently, novel camera-based physical attacks have emerged, leveraging camera patches to execute stealthy attacks. These methods circumvent target object modifications by introducing perturbations directly to the camera lens, achieving a notable breakthrough in stealthiness. However, prevailing camera-based strategies necessitate the deployment of multiple patches on the camera lens, which introduces complexity. To address this issue, we propose an Adversarial Camera Patch (ADCP).