Universal Fourier Attack for Time Series

09/02/2022
by   Elizabeth Coda, et al.
12

A wide variety of adversarial attacks have been proposed and explored using image and audio data. These attacks are notoriously easy to generate digitally when the attacker can directly manipulate the input to a model, but are much more difficult to implement in the real-world. In this paper we present a universal, time invariant attack for general time series data such that the attack has a frequency spectrum primarily composed of the frequencies present in the original data. The universality of the attack makes it fast and easy to implement as no computation is required to add it to an input, while time invariance is useful for real-world deployment. Additionally, the frequency constraint ensures the attack can withstand filtering. We demonstrate the effectiveness of the attack in two different domains, speech recognition and unintended radiated emission, and show that the attack is robust against common transform-and-compare defense pipelines.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/13/2021

Untargeted, Targeted and Universal Adversarial Attacks and Defenses on Time Series

Deep learning based models are vulnerable to adversarial attacks. These ...
research
09/20/2023

AudioFool: Fast, Universal and synchronization-free Cross-Domain Attack on Speech Recognition

Automatic Speech Recognition systems have been shown to be vulnerable to...
research
11/15/2022

Backdoor Attacks on Time Series: A Generative Approach

Backdoor attacks have emerged as one of the major security threats to de...
research
07/19/2022

Towards Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms

As deep learning models have gradually become the main workhorse of time...
research
01/27/2023

Targeted Attacks on Timeseries Forecasting

Real-world deep learning models developed for Time Series Forecasting ar...
research
11/19/2022

Phonemic Adversarial Attack against Audio Recognition in Real World

Recently, adversarial attacks for audio recognition have attracted much ...
research
08/18/2023

Compensating Removed Frequency Components: Thwarting Voice Spectrum Reduction Attacks

Automatic speech recognition (ASR) provides diverse audio-to-text servic...

Please sign up or login with your details

Forgot password? Click here to reset