Real-Time Adversarial Attacks

Abstract

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.

To Appear in the Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI 2019). Code: https://github.com/YuanGongND/realtime-adversarial-attack

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
• Did you hear that? Adversarial Examples Against Automatic Speech Recognition
• Robust Audio Adversarial Example for a Physical Attack
• Houdini: Fooling Deep Structured Prediction Models
• HotFlip: White-Box Adversarial Examples for Text Classification
• An Overview of Vulnerabilities of Voice Controlled Systems

Cited by in corpus (5)

• The Threat of Adversarial Attacks on Machine Learning in Network Security -- A Survey
• Developing Future Human-Centered Smart Cities: Critical Analysis of Smart City Security, Interpretability, and Ethical Challenges
• Adversarial Transferability in Wearable Sensor Systems
• DLBC: A Deep Learning-Based Consensus in Blockchains for Deep Learning Services
• ReMASC: Realistic Replay Attack Corpus for Voice Controlled Systems