WaveTransform: Crafting Adversarial Examples via Input Decomposition
Frequency spectrum has played a significant role in learning unique and discriminating features for object recognition. Both low and high frequency information present in images have been extracted and learnt by a host of representation learning techniques, including deep learning. Inspired by this observation, we introduce a novel class of adversarial attacks, namely `WaveTransform', that creates adversarial noise corresponding to low-frequency and high-frequency subbands, separately (or in combination). The frequency subbands are analyzed using wavelet decomposition; the subbands are corrupted and then used to construct an adversarial example. Experiments are performed using multiple databases and CNN models to establish the effectiveness of the proposed WaveTransform attack and analyze the importance of a particular frequency component. The robustness of the proposed attack is also evaluated through its transferability and resiliency against a recent adversarial defense algorithm. Experiments show that the proposed attack is effective against the defense algorithm and is also transferable across CNNs.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial DefenseObject RecognitionRepresentation LearningSimilar Papers 제목 키워드 기반
On the Robustness of Domain Constraints
Machine learning is vulnerable to adversarial examples-inputs designed to cause models to perform poorly. However, it is unclear if adversarial examples represent realistic inputs in the modeled domains. Diverse domains …
validAdversarial Robustness of Deep Reinforcement Learning based Dynamic Recommender Systems
Adversarial attacks, e.g., adversarial perturbations of the input and adversarial samples, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation systems. The l…
Adversarial RobustnesscounterfactualDeep Reinforcement LearningInteractive Recommendation+4Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
Crafting adversarial examples has become an important technique to evaluate the robustness of deep neural networks (DNNs). However, most existing works focus on attacking the image classification problem since its input …
image-classificationImage ClassificationMachine TranslationText Summarization+1Semantics Preserving Adversarial Attacks
While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge. In this paper, we propose a framework to generate semantics preserving …
Semantics Preserving Adversarial Learning
While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge. In this paper, we propose a framework to generate semantics preserving …
Text Classification