Adversarial Stress Tests for Quantum Certification

• URL: http://arxiv.org/abs/2603.12622v1
• Date: Fri, 13 Mar 2026 03:49:58 GMT
• Title: Adversarial Stress Tests for Quantum Certification
• Abstract summary: Apparent violations of classical benchmarks need not signal genuinely non-classical behaviour.<n>We formalise a protocol-agnostic alignment principle based on a martingale-safe lower confidence bound.<n>We show that adaptive learning-based classical agents do not enlarge the admissible classical set.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We develop a practical framework for semi-device-independent (SDI) certification under operational deviations from the ideal protocol model. Apparent violations of classical benchmarks need not signal genuinely non-classical behaviour; they can arise from misalignment between (i) the scoring rule, (ii) the finite-sample statistical bound applied to that score, and (iii) the operational model realised in the experiment, including bias, memory, drift, and selection effects. We formalise a protocol-agnostic alignment principle based on a martingale-safe lower confidence bound and an operationally consistent effective classical ceiling. This yields a quantitative diagnostic, the \emph{robustness gap} $Δ_{\mathrm{rob}} = S_{\mathrm{low}} - S_{C,\mathrm{eff}}$, which separates statistical fluctuations from structural modelling errors. Statistical deviations vanish asymptotically, whereas model misalignment can produce persistent false certification unless the benchmark is corrected. Using the $2\!\to\!1$ random access code as a minimal SDI testbed, we show that postselection can inflate conditional scores, whereas unconditional scoring restores the correct operational meaning of the witness. We further show that adaptive learning-based classical agents do not enlarge the admissible classical set; rather, they recover the effective classical ceiling implied by the operational model. The resulting framework provides a systematic diagnostic for certification in realistic quantum communication and measurement settings with embedded classical control, adaptive processing, and nonideal data acquisition.

Related papers

• Conformalized Large Language Models under Configuration Shift [46.502741608809174]
  Conformal prediction is a distribution-free framework for uncertainty quantification.<n>Nonconformity scores are often induced by an inference pipeline, not just a fixed model.<n>We show that configuration shift consistently erodes CP validity.
  arXiv  Detail & Related papers  (2026-08-02T19:34:41Z)
• Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning [58.088509347353465]
  Reinforcement learning (RL) fine-tuning is widely used in language model training.<n>We propose a game-theoretic framework that gives this trade-off an explicit statistical interpretation.
  arXiv  Detail & Related papers  (2026-07-29T00:19:09Z)
• Non-Parametric Rehearsal Learning via Conditional Mean Embeddings [88.89267783967263]
  We propose a non-parametric rehearsal learning approach for textitavoiding undesired future (AUF) problems.<n>Specifically, we use kernel machinery to reformulate the AUF objective into a unified representation that disentangles desirability modeling from action-induced distributional changes.
  arXiv  Detail & Related papers  (2026-05-09T15:30:52Z)
• Online Bayesian Imbalanced Learning with Bregman-Calibrated Deep Networks [0.7106986689736825]
  We present textitOnline Bayesian Imbalanced Learning (OBIL), a principled framework that decouples likelihood-ratio estimation from class-prior assumptions.<n>Our approach builds on the established connection between Bregman divergences and proper scoring rules to show that deep networks trained with such losses produce posterior probability estimates.<n>We prove that these likelihood-ratio estimates remain valid under arbitrary changes in class priors and cost structures, requiring only a threshold adjustment for optimal Bayes decisions.
  arXiv  Detail & Related papers  (2026-02-08T21:23:00Z)
• Explicit Uncertainty Modeling for Active CLIP Adaptation with Dual Prompt Tuning [51.99383151474742]
  We propose a robust uncertainty modeling framework for active CLIP adaptation based on dual-prompt tuning.<n>We show that our method consistently outperforms existing active learning methods under the same annotation budget.
  arXiv  Detail & Related papers  (2026-02-04T09:01:55Z)
• Another Fit Bites the Dust: Conformal Prediction as a Calibration Standard for Machine Learning in High-Energy Physics [0.0]
  Conformal prediction provides a distribution-free framework for calibrating arbitrary predictive models.<n>We show that a single conformal formalism can be applied across regression, binary and multi-class classification, anomaly detection, and generative modelling.<n>We argue that conformal calibration should be adopted as a standard component of machine-learning pipelines in collider physics.
  arXiv  Detail & Related papers  (2025-12-18T20:31:25Z)
• Adaptive Off-Policy Inference for M-Estimators Under Model Misspecification [32.7750904494144]
  We propose a method that provides valid inference for M-estimators that use adaptively collected bandit data.<n>A key ingredient in our approach is the use of flexible machine learning approaches to stabilize the variance induced by adaptive data collection.
  arXiv  Detail & Related papers  (2025-09-17T17:51:40Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Prediction-Powered Causal Inferences [59.98498488132307]
  We focus on Prediction-Powered Causal Inferences (PPCI)<n>We first show that conditional calibration guarantees valid PPCI at population level.<n>We then introduce a sufficient representation constraint transferring validity across experiments.
  arXiv  Detail & Related papers  (2025-02-10T10:52:17Z)
• When Does Confidence-Based Cascade Deferral Suffice? [69.28314307469381]
  Cascades are a classical strategy to enable inference cost to vary adaptively across samples. A deferral rule determines whether to invoke the next classifier in the sequence, or to terminate prediction. Despite being oblivious to the structure of the cascade, confidence-based deferral often works remarkably well in practice.
  arXiv  Detail & Related papers  (2023-07-06T04:13:57Z)
• MaxMatch: Semi-Supervised Learning with Worst-Case Consistency [149.03760479533855]
  We propose a worst-case consistency regularization technique for semi-supervised learning (SSL) We present a generalization bound for SSL consisting of the empirical loss terms observed on labeled and unlabeled training data separately. Motivated by this bound, we derive an SSL objective that minimizes the largest inconsistency between an original unlabeled sample and its multiple augmented variants.
  arXiv  Detail & Related papers  (2022-09-26T12:04:49Z)

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.