Robust Attacks against Multiple Classifiers
We address the challenge of designing optimal adversarial noise algorithms for settings where a learner has access to multiple classifiers. We demonstrate how this problem can be framed as finding strategies at equilibrium in a two-player, zero-sum game between a learner and an adversary. In doing so, we illustrate the need for randomization in adversarial attacks. In order to compute Nash equilibrium, our main technical focus is on the design of best response oracles that can then be implemented within a Multiplicative Weights Update framework to boost deterministic perturbations against a set of models into optimal mixed strategies. We demonstrate the practical effectiveness of our approach on a series of image classification tasks using both linear classifiers and deep neural networks.
Code (1)
Tasks
General Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
On The Robustness of Offensive Language Classifiers
Social media platforms are deploying machine learning based offensive language classification systems to combat hateful, racist, and other forms of offensive speech at scale. However, despite their real-world deployment,…
Optimal Attacks against Multiple Classifiers
We study the problem of designing provably optimal adversarial noise algorithms that induce misclassification in settings where a learner aggregates decisions from multiple classifiers. Given the demonstrated vulnerabili…
image-classificationImage ClassificationEnhancing Robustness of Machine Learning Systems via Data Transformations
We propose the use of data transformations as a defense against evasion attacks on ML classifiers. We present and investigate strategies for incorporating a variety of data transformations including dimensionality reduct…
BIG-bench Machine LearningClassificationDimensionality ReductionGeneral Classification+2Poisoning Network Flow Classifiers
As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, spec…
T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification
Deep Neural Network (DNN) classifiers are known to be vulnerable to Trojan or backdoor attacks, where the classifier is manipulated such that it misclassifies any input containing an attacker-determined Trojan trigger. B…
text-classificationText Classification