On the Similarity of Deep Learning Representations Across Didactic and Adversarial Examples
The increasing use of deep neural networks (DNNs) has motivated a parallel endeavor: the design of adversaries that profit from successful misclassifications. However, not all adversarial examples are crafted for malicious purposes. For example, real world systems often contain physical, temporal, and sampling variability across instrumentation. Adversarial examples in the wild may inadvertently prove deleterious for accurate predictive modeling. Conversely, naturally occurring covariance of image features may serve didactic purposes. Here, we studied the stability of deep learning representations for neuroimaging classification across didactic and adversarial conditions characteristic of MRI acquisition variability. We show that representational similarity and performance vary according to the frequency of adversarial examples in the input space.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity
Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset genera…
Adversarial AttackSemantic SimilaritySemantic Textual SimilarityLost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation
Language Models today provide a high accuracy across a large number of downstream tasks. However, they remain susceptible to adversarial attacks, particularly against those where the adversarial examples maintain conside…
Machine TranslationTranslationUnderstanding Robust Learning through the Lens of Representation Similarities
Representation learning, i.e. the generation of representations useful for downstream applications, is a task of fundamental importance that underlies much of the success of deep neural networks (DNNs). Recently, robustn…
Representation LearningBoosting Imperceptibility of Stable Diffusion-based Adversarial Examples Generation with Momentum
We propose a novel framework, Stable Diffusion-based Momentum Integrated Adversarial Examples (SD-MIAE), for generating adversarial examples that can effectively mislead neural network classifiers while maintaining visua…
Image GenerationSemantic SimilaritySemantic Textual SimilarityText to Image Generation+1R&R: Metric-guided Adversarial Sentence Generation
Adversarial examples are helpful for analyzing and improving the robustness of text classifiers. Generating high-quality adversarial examples is a challenging task as it requires generating fluent adversarial sentences t…
Adversarial AttackGeneral ClassificationSemantic SimilaritySemantic Textual Similarity+4