Concealed Adversarial attacks on neural networks for sequential data

TL;DR

This paper introduces a concealed adversarial attack method for time series neural networks that produces realistic, hard-to-detect perturbations, challenging current robustness defenses across multiple architectures.

Contribution

It develops a novel attack that maximizes classifier and discriminator loss, with a training procedure for broader attack coverage, improving concealability and effectiveness.

Findings

The attack outperforms existing methods in concealability and efficiency.

Benchmark results on six datasets show superior attack performance.

The study highlights the need for stronger defenses against realistic adversarial attacks.

Abstract

The emergence of deep learning led to the broad usage of neural networks in the time series domain for various applications, including finance and medicine. While powerful, these models are prone to adversarial attacks: a benign targeted perturbation of input data leads to significant changes in a classifier's output. However, formally small attacks in the time series domain become easily detected by the human eye or a simple detector model. We develop a concealed adversarial attack for different time-series models: it provides more realistic perturbations, being hard to detect by a human or model discriminator. To achieve this goal, the proposed adversarial attack maximizes an aggregation of a classifier and a trained discriminator loss. To make the attack stronger, we also propose a training procedure for a discriminator that provides broader coverage of possible attacks. Extensive benchmarking on six UCR time series datasets across four diverse architectures - including recurrent, convolutional, state-space, and transformer-based models - demonstrates the superiority of our attack for a concealability-efficiency trade-off. Our findings highlight the growing challenge of designing robust time series models, emphasizing the need for improved defenses against realistic and effective attacks.