Adversarial attack aims to generate infinitesimal perturbations that are crafted to deceive well-trained classifiers, and has been extensively explored in the context of classical data. However, the generation of adversarial attacks for quantum data remains largely unexplored. This work addresses this gap by investigating the efficacy of classical adversarial attack generation methods in the realm of quantum data learning. Specifically, we implement two widely recognized adversarial attack generation techniques, namely, the fast gradient sign method (FGSM) and the Deepfool method, for generating adversarial attacks on quantum data based on Gell-Mann matrices. We further evaluate the deceptive capabilities of these generated adversarial samples on a classical classifier tasked with entanglement discrimination. Through extensive numerical simulations, we demonstrate the effectiveness of our adversarial attack generation methods in efficiently crafting adversarial attacks on quantum data, successfully fooling the well-trained classifier. The outcomes of our research not only extend the applicability of classical machine learning algorithms to the domain of quantum machine learning but also provide valuable insights into the vulnerability of quantum data.
Adversarial attack aims to generate infinitesimal perturbations that are crafted to deceive well-trained classifiers, and has been extensively explored in the context of classical data. However, the generation of adversarial attacks for quantum data remains largely unexplored. This work addresses this gap by investigating the efficacy of classical adversarial attack generation methods in the realm of quantum data learning. Specifically, we implement two widely recognized adversarial attack generation techniques, namely, the fast gradient sign method (FGSM) and the Deepfool method, for generating adversarial attacks on quantum data based on Gell-Mann matrices. We further evaluate the deceptive capabilities of these generated adversarial samples on a classical classifier tasked with entanglement discrimination. Through extensive numerical simulations, we demonstrate the effectiveness of our adversarial attack generation methods in efficiently crafting adversarial attacks on quantum data, successfully fooling the well-trained classifier. The outcomes of our research not only extend the applicability of classical machine learning algorithms to the domain of quantum machine learning but also provide valuable insights into the vulnerability of quantum data.
Quantum machine learning, noted for its remarkable advancements in enhancing computational speed and augmenting data processing efficacy, is acquiring considerable recognition within the scientific community. Despite the noteworthy advancements of quantum machine learning, it shares with its traditional counterpart a susceptibility to adversarial threats. This presents a significant challenge and underscores the need for robust countermeasures in this emerging field of study. Developing effective adversarial attack algorithms, such as the Quantum Fast Gradient Sign Method (QFGSM), is crucial to opening the path for exploring robust defense mechanisms against these threats. However, unlike traditional machine learning, the quantum field currently lacks the effective techniques to orchestrate adversarial attacks. This study introduces and assesses the QFGSM, a adversarial attack algorithm tailored for QNNs. Additionally, we evaluate the effect of random noise and its quantum version on these models, providing a comprehensive comparison to understand the efficacy of adversarial attack methods. The evaluation is conducted on both traditional Neural Networks (NNs) and QNNs using the ClaMP dataset, a cybersecurity-focused dataset, and involves performance metrics like Accuracy, Precision, Recall, and F1 score. Our findings underscore the differential resilience of NNs and QNNs under adversarial attacks and reveal the contrasting effects of FGSM, QFGSM, and random noise-based methods. Our study reveals that Quantum Neural Networks (QNNs) show significant vulnerability to our proposed Quantum Fast Gradient Sign Method (QFGSM) compared to random noise, indicating a need for quantum-specific defenses in the face of this advanced adversarial attack algorithm.
Abstract We show that hybrid quantum classifiers based on quantum kernel methods and support vector machines are vulnerable against adversarial attacks, namely small engineered perturbations of the input data can deceive the classifier into predicting the wrong result. Nonetheless, we also show that simple defense strategies based on data augmentation with a few crafted perturbations can make the classifier robust against new attacks. Our results find applications in security-critical learning problems and in mitigating the effect of some forms of quantum noise, since the attacker can also be understood as part of the surrounding environment.
Quantum Machine Learning (QML) fuses quantum computing with machine learning to address complex tasks with potential speedups over classical methods. While QML models such as variational quantum classifiers (QVC), quantum multilayer perceptron(QMLP) models and quantum convolutional neural networks (QCNN) have demonstrated promise in applications like image recognition and malware classification, they remain vulnerable to adversarial threats. Inspired by the vulnerabilities in classical ML, this work systematically investigates how attacks-ranging from training-time poisoning and inferencetime evasion (e.g., quantum versions of FGSM and PGD) to deployment-time trigger attacks-manifest in quantum circuits. We explore how classical adversarial strategies adapt to quantum models through parameterized encodings, hybrid architectures, and probabilistic outputs. The poster evaluates different quantum classifiers under adversarial settings, comparing their robustness, trainability, and resilience to perturbations. Defense mechanisms such as randomized encoding, engineered noise channels, and quantum adversarial training are analyzed in relation to specific threat types. In addition, we assess how quantum models behave differently than classical counterparts under attack, and how quantum-specific design constraints can either exacerbate or mitigate these effects. Our ultimate goal is to define and construct robust QML systems that are both theoretically sound and practically secure. By synthesizing results across multiple QML architectures and threat models, this work provides actionable insight into the development of resilient quantum classifiers, paving the way toward trustworthy and scalable quantum machine learning.
Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as by insertion of carefully crafted noise, it can cause the model to make mistakes. Quantum machine learning models are also vulnerable to such adversarial attacks, especially in image classification using variational quantum classifiers. While there are promising defenses against these adversarial perturbations, such as training with adversarial samples, they face practical limitations. For example, they are not applicable in scenarios where training with adversarial samples is either not possible or can overfit the models on one type of attack. In this paper, we propose an adversarial training-free defense framework that utilizes a quantum autoencoder to purify the adversarial samples through reconstruction. Moreover, our defense framework provides a confidence metric to identify potentially adversarial samples that cannot be purified the quantum autoencoder. Extensive evaluation demonstrates that our defense framework can significantly outperform state-of-the-art in prediction accuracy (up to 68%) under adversarial attacks.
Abstract Quantum machine learning explores the interplay between machine learning and quantum physics, which may lead to unprecedented perspectives for both fields. In fact, recent works have shown strong evidences that quantum computers could outperform classical computers in solving certain notable machine learning tasks. Yet, quantum learning systems may also suffer from the vulnerability problem: adding a tiny carefully-crafted perturbation to the legitimate input data would cause the systems to make incorrect predictions at a notably high confidence level. In this paper, we study the universality of adversarial examples and perturbations for quantum classifiers. Through concrete examples involving classifications of real-life images and quantum phases of matter, we show that there exist universal adversarial examples that can fool a set of different quantum classifiers. We prove that for a set of k classifiers with each receiving input data of n qubits, an O(2nlnk) increase of the perturbation strength is enough to ensure a moderate universal adversarial risk. In addition, for a given quantum classifier we show that there exist universal adversarial perturbations, which can be added to different legitimate samples and make them to be adversarial examples for the classifier. Our results reveal the universality perspective of adversarial attacks for quantum machine learning systems, which would be crucial for practical applications of both near-term and future quantum technologies in solving machine learning problems.
Abstract 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.