Adversarial Attacks, Regression, and Numerical Stability Regularization

2018/12/07 by André T. Nguyen, Edward Raff, Nguyen, Andre T. +1 · 3 citations
Computer Science · Physics and Astronomy · #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks

paper · pdf · doi:10.48550/arxiv.1812.02885

openalex publication_date 2018/12/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Adversarial attacks against neural networks in a regression setting are a critical yet understudied problem. In this work, we advance the state of the art by investigating adversarial attacks against regression networks and by formulating a more effective defense against these attacks. In particular, we take the perspective that adversarial attacks are likely caused by numerical instability in learned functions. We introduce a stability inducing, regularization based defense against adversarial attacks in the regression setting. Our new and easy to implement defense is shown to outperform prior approaches and to improve the numerical stability of learned functions.

Cited by

• Are Inherently Interpretable Models More Robust? A Study In Music Emotion Recognition
• Adversarial Machine Learning Attacks on Financial Reporting via Maximum Violated Multi-Objective Attack
• What is Adversarial Training for Diffusion Models?

Related

• Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples
• Towards Robust Training of Neural Networks by Regularizing Adversarial Gradients
• Scaling up the randomized gradient-free adversarial attack reveals\n overestimation of robustness using established attacks
• Attacking Adversarial Attacks as A Defense
• On Neural Network approximation of ideal adversarial attack and convergence of adversarial training