Non-Negative Networks Against Adversarial Attacks
Adversarial attacks against neural networks are a problem of considerable importance, for which effective defenses are not yet readily available. We make progress toward this problem by showing that non-negative weight constraints can be used to improve resistance in specific scenarios. In particular, we show that they can provide an effective defense for binary classification problems with asymmetric cost, such as malware or spam detection. We also show the potential for non-negativity to be helpful to non-binary problems by applying it to image classification.
Code (1)
Tasks
Binary ClassificationClassificationGeneral Classificationimage-classificationImage ClassificationSpam detectionSimilar Papers 제목 키워드 기반
Adversarial Examples for Extreme Multilabel Text Classification
Extreme Multilabel Text Classification (XMTC) is a text classification problem in which, (i) the output space is extremely large, (ii) each data point may have multiple positive labels, and (iii) the data follows a stron…
ClassificationMultilabel Text ClassificationRecommendation Systemstext-classification+1Randomization matters. How to defend against strong adversarial attacks
Is there a classifier that ensures optimal robustness against all adversarial attacks? This paper answers this question by adopting a game-theoretic point of view. We show that adversarial attacks and defenses form an in…
Randomization matters How to defend against strong adversarial attacks
\emph{Is there a classifier that ensures optimal robustness against all adversarial attacks?} This paper answers this question by adopting a game-theoretic point of view. We show that adversarial attacks and defenses for…
Transferring Robustness for Graph Neural Network Against Poisoning Attacks
Graph neural networks (GNNs) are widely used in many applications. However, their robustness against adversarial attacks is criticized. Prior studies show that using unnoticeable modifications on graph topology or nodal …
Graph Neural NetworkNode ClassificationTransfer LearningMal2GCN: A Robust Malware Detection Approach Using Deep Graph Convolutional Networks With Non-Negative Weights
With the growing pace of using Deep Learning (DL) to solve various problems, securing these models against adversaries has become one of the main concerns of researchers. Recent studies have shown that DL-based malware d…
Malware Detection