Mathematical Analysis of Adversarial Attacks

2018-11-15 · Zehao Dou, Stanley J. Osher, Bao Wang

In this paper, we analyze efficacy of the fast gradient sign method (FGSM) and the Carlini-Wagner's L2 (CW-L2) attack. We prove that, within a certain regime, the untargeted FGSM can fool any convolutional neural nets (CNNs) with ReLU activation; the targeted FGSM can mislead any CNNs with ReLU activation to classify any given image into any prescribed class. For a special two-layer neural network: a linear layer followed by the softmax output activation, we show that the CW-L2 attack increases the ratio of the classification probability between the target and ground truth classes. Moreover, we provide numerical results to verify all our theoretical results.

📄 PDF Abstract BibTeX arXiv:1811.06492

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Algebraic Adversarial Attacks on Explainability Models

2025-03-16 · Lachlan Simpson, Federico Costanza, Kyle Millar, Adriel Cheng 외

Classical adversarial attacks are phrased as a constrained optimisation problem. Despite the efficacy of a constrained optimisation approach to adversarial attacks, one cannot trace how an adversarial point was generated…

Adversarial Machine Learning: Attacks, Defenses, and Open Challenges

2025-02-08 · Pranav K Jha

Adversarial Machine Learning (AML) addresses vulnerabilities in AI systems where adversaries manipulate inputs or training data to degrade performance. This article provides a comprehensive analysis of evasion and poison…

Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks

2021-09-29 · Kaleel Mahmood, Rigel Mahmood, Ethan Rathbun, Marten van Dijk

The field of adversarial machine learning has experienced a near exponential growth in the amount of papers being produced since 2018. This massive information output has yet to be properly processed and categorized. In …

BIG-bench Machine Learning

Algebraic Adversarial Attacks on Integrated Gradients

2024-07-23 · Lachlan Simpson, Federico Costanza, Kyle Millar, Adriel Cheng 외

Adversarial attacks on explainability models have drastic consequences when explanations are used to understand the reasoning of neural networks in safety critical systems. Path methods are one such class of attribution …

Security Analysis and Enhancement of Model Compressed Deep Learning Systems under Adversarial Attacks

2018-02-14 · Qi Liu, Tao Liu, Zihao Liu, Yanzhi Wang 외

DNN is presenting human-level performance for many complex intelligent tasks in real-world applications. However, it also introduces ever-increasing security concerns. For example, the emerging adversarial attacks indica…

Adversarial Attack