Detecting Adversarial Examples through Nonlinear Dimensionality Reduction
Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. This work proposes a detection method based on combining non-linear dimensionality reduction and density estimation techniques. Our empirical findings show that the proposed approach is able to effectively detect adversarial examples crafted by non-adaptive attackers, i.e., not specifically tuned to bypass the detection method. Given our promising results, we plan to extend our analysis to adaptive attackers in future work.
Code (1)
Tasks
Density EstimationDimensionality ReductionGeneral ClassificationSimilar Papers 제목 키워드 기반
The Role of Input Dimensionality in the Emergence and Targeted Control of Adversarial Examples
Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry. However, the assumptions underlying these works are rarely examined e…
Interpretable Dimensionality Reduction by Feature Preserving Manifold Approximation and Projection
Nonlinear dimensionality reduction lacks interpretability due to the absence of source features in low-dimensional embedding space. We propose an interpretable method featMAP to preserve source features by tangent space …
Dimensionality ReductionFeature Importanceobject-detectionObject DetectionDetecting Textual Adversarial Examples Based on Distributional Characteristics of Data Representations
Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, succe…
SentenceFrequency-Guided Word Substitutions for Detecting Textual Adversarial Examples
Recent efforts have shown that neural text processing models are vulnerable to adversarial examples, but the nature of these examples is poorly understood. In this work, we show that adversarial attacks against CNN, LSTM…
General ClassificationSST-2Text ClassificationNot All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding
Detecting adversarial examples currently stands as one of the biggest challenges in the field of deep learning. Adversarial attacks, which produce adversarial examples, increase the prediction likelihood of a target clas…
All