Consistent Semantic Attacks on Optical Flow
This addresses security vulnerabilities in optical flow systems, which are incremental by building on existing adversarial attack methods with a focus on output consistency.
The paper tackles the problem of creating adversarial attacks on optical flow models that are consistent in the output to hide the attacker's intent, achieving effectiveness in both white-box and black-box settings and on subsequent dependent tasks.
We present a novel approach for semantically targeted adversarial attacks on Optical Flow. In such attacks the goal is to corrupt the flow predictions of a specific object category or instance. Usually, an attacker seeks to hide the adversarial perturbations in the input. However, a quick scan of the output reveals the attack. In contrast, our method helps to hide the attackers intent in the output as well. We achieve this thanks to a regularization term that encourages off-target consistency. We perform extensive tests on leading optical flow models to demonstrate the benefits of our approach in both white-box and black-box settings. Also, we demonstrate the effectiveness of our attack on subsequent tasks that depend on the optical flow.