NetFlick: Adversarial Flickering Attacks on Deep Learning Based Video Compression. (arXiv:2304.01441v1 [eess.IV])

Video compression plays a significant role in IoT devices for the efficient
transport of visual data while satisfying all underlying bandwidth constraints.
Deep learning-based video compression methods are rapidly replacing traditional
algorithms and providing state-of-the-art results on edge devices. However,
recently developed adversarial attacks demonstrate that digitally crafted
perturbations can break the Rate-Distortion relationship of video compression.
In this work, we present a real-world LED attack to target video compression
frameworks. Our physically realizable attack, dubbed NetFlick, can degrade the …

adversarial adversarial attacks algorithms art attack attacks bandwidth compression constraints correlation data deep learning devices edge edge devices frameworks iot iot devices rate relationship results role state target temporal transport video work world