RobQFL: Robust Quantum Federated Learning in Adversarial Environment

• URL: http://arxiv.org/abs/2509.04914v1
• Date: Fri, 05 Sep 2025 08:28:10 GMT
• Title: RobQFL: Robust Quantum Federated Learning in Adversarial Environment
• Authors: Walid El Maouaki, Nouhaila Innan, Alberto Marchisio, Taoufik Said, Muhammad Shafique, Mohamed Bennai,
• Abstract summary: We propose Robust Quantum Federated Learning (RobQFL), embedding adversarial training directly into the federated loop.<n>RobQFL exposes tunable axes: client coverage, perturbation scheduling, and optimization.<n>On 15-client simulations with MNIST and Fashion-MNIST, IID and Non-IID conditions, training only 20-50% clients adversarially boosts $varepsilon leq 0.1$ accuracy.<n>With $geq$75% coverage, a moderate $varepsilon$-mix is optimal, while high-$varepsilon$ schedules help only to 100
• Score: 2.048164304914359
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantum Federated Learning (QFL) merges privacy-preserving federation with quantum computing gains, yet its resilience to adversarial noise is unknown. We first show that QFL is as fragile as centralized quantum learning. We propose Robust Quantum Federated Learning (RobQFL), embedding adversarial training directly into the federated loop. RobQFL exposes tunable axes: client coverage $\gamma$ (0-100\%), perturbation scheduling (fixed-$\varepsilon$ vs $\varepsilon$-mixes), and optimization (fine-tune vs scratch), and distils the resulting $\gamma \times \varepsilon$ surface into two metrics: Accuracy-Robustness Area and Robustness Volume. On 15-client simulations with MNIST and Fashion-MNIST, IID and Non-IID conditions, training only 20-50\% clients adversarially boosts $\varepsilon \leq 0.1$ accuracy $\sim$15 pp at $< 2$ pp clean-accuracy cost; fine-tuning adds 3-5 pp. With $\geq$75\% coverage, a moderate $\varepsilon$-mix is optimal, while high-$\varepsilon$ schedules help only at 100\% coverage. Label-sorted non-IID splits halve robustness, underscoring data heterogeneity as a dominant risk.

Related papers

• Sublinear Time Quantum Sensitivity Sampling [57.356528942341534]
  We present a unified framework for quantum sensitivity sampling, extending the advantages of quantum computing to a broad class of classical approximation problems.<n>Our framework provides a streamlined approach for constructing coresets and offers significant runtime improvements in applications such as clustering, regression, and low-rank approximation.
  arXiv  Detail & Related papers  (2025-09-20T20:18:49Z)
• Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits [55.957560311008926]
  We propose a piecewise stationary linear bandit (PSLB) model where the quality of an arm is measured by its return averaged over all contexts. PS$varepsilon$BAI$+$ is guaranteed to identify an $varepsilon$-optimal arm with probability $ge 1-delta$ and with a minimal number of samples.
  arXiv  Detail & Related papers  (2024-10-10T06:15:42Z)
• Federated Frank-Wolfe Algorithm [7.124736158080938]
  We propose a Federated FrankWolfe Algorithm (FedFW) for constrained machine learning problems. FedFW features data privacy, low per-it cost, sparse communication, and iterations. We show that FedFW finds a solution within $O(varepsilon-3)$ in the convex setting.
  arXiv  Detail & Related papers  (2024-08-19T15:31:06Z)
• RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness [4.188296977882316]
  We propose a novel training framework textbfRAMP, to boost the robustness against multiple $l_p$ perturbations. For training from scratch, textbfRAMP achieves a union accuracy of $44.6%$ and good clean accuracy of $81.2%$ on ResNet-18 against AutoAttack on CIFAR-10.
  arXiv  Detail & Related papers  (2024-02-09T23:29:54Z)
• S-BDT: Distributed Differentially Private Boosted Decision Trees [1.4785572573908556]
  We introduce S-BDT: a novel $(varepsilon,delta)$-differentially private distributed gradient boosted decision tree (GBDT) learner. S-BDT uses less noise by relying on non-spherical multivariate Gaussian noise. We show that for situations where a GBDT is learning a stream of data that originates from different subpopulations, S-BDT improves the saving of epsilon even further.
  arXiv  Detail & Related papers  (2023-09-21T13:09:10Z)
• Succinct quantum testers for closeness and $k$-wise uniformity of probability distributions [2.3466828785520373]
  We explore potential quantum speedups for the fundamental problem of testing the properties of closeness and $k$-wise uniformity of probability distributions. We show that the quantum query complexities for $ell1$- and $ell2$-closeness testing are $O(sqrtn/varepsilon)$ and $O(sqrtnk/varepsilon)$. We propose the first quantum algorithm for this problem with query complexity $O(sqrtnk/varepsilon)
  arXiv  Detail & Related papers  (2023-04-25T15:32:37Z)
• Near Sample-Optimal Reduction-based Policy Learning for Average Reward MDP [58.13930707612128]
  This work considers the sample complexity of obtaining an $varepsilon$-optimal policy in an average reward Markov Decision Process (AMDP) We prove an upper bound of $widetilde O(H varepsilon-3 ln frac1delta)$ samples per state-action pair, where $H := sp(h*)$ is the span of bias of any optimal policy, $varepsilon$ is the accuracy and $delta$ is the failure probability.
  arXiv  Detail & Related papers  (2022-12-01T15:57:58Z)
• Improved techniques for deterministic l2 robustness [63.34032156196848]
  Training convolutional neural networks (CNNs) with a strict 1-Lipschitz constraint under the $l_2$ norm is useful for adversarial robustness, interpretable gradients and stable training. We introduce a procedure to certify robustness of 1-Lipschitz CNNs by replacing the last linear layer with a 1-hidden layer. We significantly advance the state-of-the-art for standard and provable robust accuracies on CIFAR-10 and CIFAR-100.
  arXiv  Detail & Related papers  (2022-11-15T19:10:12Z)
• Distributed DP-Helmet: Scalable Differentially Private Non-interactive Averaging of Single Layers [1.1111555270277715]
  We propose two differentially private, non-interactive, distributed learning algorithms in a framework called Distributed DP-Helmet. We provide experimental evidence that blind averaging for SVMs and single Softmax-layer (Softmax-SLP) can have a strong utility-privacy tradeoff.
  arXiv  Detail & Related papers  (2022-11-03T17:16:20Z)
• Differentially Private Deep Learning with ModelMix [14.445182641912014]
  We propose a generic optimization framework, called em ModelMix, which performs random aggregation of intermediate model states. It strengthens the composite privacy analysis utilizing the entropy of the training trajectory. We present a formal study on the effect of gradient clipping in Differentially Private Gradient Descent.
  arXiv  Detail & Related papers  (2022-10-07T22:59:00Z)
• Minimax-Optimal Multi-Agent RL in Zero-Sum Markov Games With a Generative Model [50.38446482252857]
  Two-player zero-sum Markov games are arguably the most basic setting in multi-agent reinforcement learning. We develop a learning algorithm that learns an $varepsilon$-approximate Markov NE policy using $$ widetildeObigg. We derive a refined regret bound for FTRL that makes explicit the role of variance-type quantities.
  arXiv  Detail & Related papers  (2022-08-22T17:24:55Z)
• Quantum Differentially Private Sparse Regression Learning [132.1981461292324]
  We devise an efficient quantum differentially private (QDP) Lasso estimator to solve sparse regression tasks. Last, we exhibit that the QDP Lasso attains a near-optimal utility bound $tildeO(N-2/3)$ with privacy guarantees.
  arXiv  Detail & Related papers  (2020-07-23T10:50:42Z)
• Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity [59.34067736545355]
  Given an MDP with $S$ states, $A$ actions, the discount factor $gamma in (0,1)$, and an approximation threshold $epsilon > 0$, we provide a model-free algorithm to learn an $epsilon$-optimal policy. For small enough $epsilon$, we show an improved algorithm with sample complexity.
  arXiv  Detail & Related papers  (2020-06-06T13:34:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.