Universal adversarial perturbations for multiple classification tasks with quantum classifiers
Quantum adversarial machine learning is an emerging field that studies the vulnerability of quantum learning systems against adversarial perturbations and develops possible defense strategies. Quantum universal adversarial perturbations are small perturbations, which can make different input samples into adversarial examples that may deceive a given quantum classifier. This is a field that was rarely looked into but worthwhile investigating because universal perturbations might simplify malicious attacks to a large extent, causing unexpected devastation to quantum machine learning models. In this paper, we take a step forward and explore the quantum universal perturbations in the context of heterogeneous classification tasks. In particular, we find that quantum classifiers that achieve almost state-of-the-art accuracy on two different classification tasks can be both conclusively deceived by one carefully-crafted universal perturbation. This result is explicitly demonstrated with well-designed quantum continual learning models with elastic weight consolidation method to avoid catastrophic forgetting, as well as real-life heterogeneous datasets from hand-written digits and medical MRI images. Our results provide a simple and efficient way to generate universal perturbations on heterogeneous classification tasks and thus would provide valuable guidance for future quantum learning technologies.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningQuantum Machine LearningSimilar Papers 제목 키워드 기반
Universal adversarial examples in speech command classification
Adversarial examples are inputs intentionally perturbed with the aim of forcing a machine learning model to produce a wrong prediction, while the changes are not easily detectable by a human. Although this topic has been…
Classificationdomain classificationGeneral ClassificationUniversal Adversarial Perturbations Against Semantic Image Segmentation
While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated speci…
image-classificationImage ClassificationImage SegmentationSegmentation+1Real-time Detection of Practical Universal Adversarial Perturbations
Universal Adversarial Perturbations (UAPs) are a prominent class of adversarial examples that exploit the systemic vulnerabilities and enable physically realizable and robust attacks against Deep Neural Networks (DNNs). …
Blockingimage-classificationImage Classificationobject-detection+1Generalizable Data-free Objective for Crafting Universal Adversarial Perturbations
Machine learning models are susceptible to adversarial perturbations: small changes to input that can cause large changes in output. It is also demonstrated that there exist input-agnostic perturbations, called universal…
Adversarial AttackDepth EstimationObject RecognitionSemantic SegmentationDefending Against Universal Perturbations With Shared Adversarial Training
Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of image class…
image-classificationImage ClassificationSemantic Segmentation