AdvDrop: Adversarial Attack to DNNs by Dropping Information
Human can easily recognize visual objects with lost information: even losing most details with only contour reserved, e.g. cartoon. However, in terms of visual perception of Deep Neural Networks (DNNs), the ability for recognizing abstract objects (visual objects with lost information) is still a challenge. In this work, we investigate this issue from an adversarial viewpoint: will the performance of DNNs decrease even for the images only losing a little information? Towards this end, we propose a novel adversarial attack, named \textit{AdvDrop}, which crafts adversarial examples by dropping existing information of images. Previously, most adversarial attacks add extra disturbing information on clean images explicitly. Opposite to previous works, our proposed work explores the adversarial robustness of DNN models in a novel perspective by dropping imperceptible details to craft adversarial examples. We demonstrate the effectiveness of \textit{AdvDrop} by extensive experiments, and show that this new type of adversarial examples is more difficult to be defended by current defense systems.
Code (1)
Tasks
Adversarial AttackAdversarial RobustnessSimilar Papers 제목 키워드 기반
General Debiasing for Graph-based Collaborative Filtering via Adversarial Graph Dropout
Graph neural networks (GNNs) have shown impressive performance in recommender systems, particularly in collaborative filtering (CF). The key lies in aggregating neighborhood information on a user-item interaction graph t…
Collaborative FilteringRecommendation SystemsRepresentation LearningNetwork Moments: Extensions and Sparse-Smooth Attacks
The impressive performance of deep neural networks (DNNs) has immensely strengthened the line of research that aims at theoretically analyzing their effectiveness. This has incited research on the reaction of DNNs to noi…
KNN-Defense: Defense against 3D Adversarial Point Clouds using Nearest-Neighbor Search
Deep neural networks (DNNs) have demonstrated remarkable performance in analyzing 3D point cloud data. However, their vulnerability to adversarial attacks-such as point dropping, shifting, and adding-poses a critical cha…
Semantic SimilaritySemantic Textual SimilarityCharacterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation
Deep Neural Networks (DNNs) have been widely applied in various recognition tasks. However, recently DNNs have been shown to be vulnerable against adversarial examples, which can mislead DNNs to make arbitrary incorrect …
General ClassificationSegmentationSemantic SegmentationNetwork Fault-tolerant and Byzantine-resilient Social Learning via Collaborative Hierarchical Non-Bayesian Learning
As the network scale increases, existing fully distributed solutions start to lag behind the real-world challenges such as (1) slow information propagation, (2) network communication failures, and (3) external adversaria…