Temporal-Distributed Backdoor Attack Against Video Based Action Recognition. (arXiv:2308.11070v2 [cs.CV] UPDATED)

Deep neural networks (DNNs) have achieved tremendous success in various
applications including video action recognition, yet remain vulnerable to
backdoor attacks (Trojans). The backdoor-compromised model will mis-classify to
the target class chosen by the attacker when a test instance (from a non-target
class) is embedded with a specific trigger, while maintaining high accuracy on
attack-free instances. Although there are extensive studies on backdoor attacks
against image data, the susceptibility of video-based systems under backdoor
attacks remains largely unexplored. Current studies …

action applications attack attacks backdoor backdoor attacks class compromised distributed embedded instance networks neural networks non recognition target temporal test trigger trojans video vulnerable