Real-Time Adversarial Attacks

by   Yuan Gong, et al.
University of Notre Dame

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.


page 1

page 2

page 3

page 4


Adversarial Reprogramming of Neural Networks

Deep neural networks are susceptible to adversarial attacks. In computer...

ROOM: Adversarial Machine Learning Attacks Under Real-Time Constraints

Advances in deep learning have enabled a wide range of promising applica...

When Bots Take Over the Stock Market: Evasion Attacks Against Algorithmic Traders

In recent years, machine learning has become prevalent in numerous tasks...

Manipulating SGD with Data Ordering Attacks

Machine learning is vulnerable to a wide variety of different attacks. I...

Attack Strength vs. Detectability Dilemma in Adversarial Machine Learning

As the prevalence and everyday use of machine learning algorithms, along...

Spatially Correlated Patterns in Adversarial Images

Adversarial attacks have proved to be the major impediment in the progre...

Please sign up or login with your details

Forgot password? Click here to reset