Quantum Machine Learning (QML) has emerged as a promising field of research, aiming to leverage the capabilities of quantum computing to enhance existing machine learning methodologies. Recent studies have revealed that, like their classical counterparts, QML models based on Parametrized Quantum Circuits (PQCs) are also vulnerable to adversarial attacks. Moreover, the existence of Universal Adversarial Perturbations (UAPs) in the quantum domain has been demonstrated theoretically in the context of quantum classifiers. In this work, we introduce QuGAP: a novel framework for generating UAPs for quantum classifiers. We conceptualize the notion of additive UAPs for PQC-based classifiers and theoretically demonstrate their existence. We then utilize generative models (QuGAP-A) to craft additive UAPs and experimentally show that quantum classifiers are susceptible to such attacks. Moreover, we formulate a new method for generating unitary UAPs (QuGAP-U) using quantum generative models and a novel loss function based on fidelity constraints. We evaluate the performance of the proposed framework and show that our method achieves state-of-the-art misclassification rates, while maintaining high fidelity between legitimate and adversarial samples.

In the problem of task allocation, form of probabilistic response tendencies can be used to redundancy refers to extra agents beyond the minimum achieve redundancy when an MAS is working on a problem number of required agents that have the capability to perform in which experience is beneficial. We assume that the MAS a given task. Particularly in problems where experience is a response threshold system (Bonabeau, Theraulaz, and is beneficial, redundancy provides an MAS with a Deneubourg 1998) and that previous experience on a task backup pool of ready actors if the primary actors are unavailable improves an agent's future performance on that task.