When cheap gradients fail: the measurement cost of attacking quantum classifiers
Adversarial perturbations threaten machine learning classifiers, including variational quantum classifiers. We show that finite quantum measurement statistics (shot noise) act as a built-in defense against gradient-based test-time attacks whose cost scales unfavorably for the attacker. Because every gradient component must be inferred from repeated circuit executions under any unbiased gradient-estimation rule, white-box extraction consumes a dimension-dependent measurement budget that measureme
Record details
Published: 13 July 2026
Source: arXiv cs.CR (AI security)
Category: Research
Topics: Military & security
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
A Guide to the Convergence of Electronic Warfare and Cyber Operations
Carnegie Mellon Software Engineering Institute · 13 July 2026
UCL joins new Defence Universities Alliance
UCL Centre for Data Ethics and Innovation · 12 July 2026
Distributed Denial of Science: How Indirect Data Poisoning of AI Systems Can Industrialize Scientific Fraud
arXiv · 12 July 2026
Internet of Agentic Things: Networked AI Agents for Closed-Loop IoT Orchestration
arXiv · 14 July 2026
Threat Vectors and the State of the Art in Defense Methods for Security in Neurotechnology
arXiv cs.CR (AI security) · 11 July 2026
Online consent misread: A mixed-method study on (cyber)rape culture's influence on sexual consent perceptions and responses to unsolicited genital images
Computers in Human Behavior · 14 July 2026
How to cite this record
ethics.ai (13 July 2026), “When cheap gradients fail: the measurement cost of attacking quantum classifiers,” evidence record 3010, https://ethics.ai/record/3010 (originally published by arXiv cs.CR (AI security)).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.