Real-Time Adversarial Attacks
This work addresses a specific limitation in adversarial attack methods for streaming data, representing an incremental advancement in the field.
The paper tackles the problem of adversarial attacks on machine learning models with streaming inputs, proposing a real-time attack scheme to address scenarios where only past data points are observable.
In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on the input can make them fail. While these attack methods are very effective, they only focus on scenarios where the target model takes static input, i.e., an attacker can observe the entire original sample and then add a perturbation at any point of the sample. These attack approaches are not applicable to situations where the target model takes streaming input, i.e., an attacker is only able to observe past data points and add perturbations to the remaining (unobserved) data points of the input. In this paper, we propose a real-time adversarial attack scheme for machine learning models with streaming inputs.