analiza aiqbench
This research addresses critical privacy vulnerabilities in clinical machine learning by demonstrating that even simple models like logistic regression are susceptible to membership inference attacks capable of identifying individual patients. The authors propose a quantum-inspired defense using tensor train representations to obfuscate model parameters while maintaining accuracy and interpretability, offering a practical alternative to differential privacy for sensitive healthcare applications.
Private and interpretable clinical prediction with quantum-inspired tensor train models
arXiv:2602.06110v2 Announce Type: replace-cross Abstract: Publicly available clinical machine learning models pose an underappreciated privacy risk: their parameters or outputs can be exploited to recover information from patients whose data were used during training. Moreover, this risk is exacerbated by models such as logistic regression (LR), which are typically preferred in clinical settings for their transparency. To assess this empirically, we attack LORIS, a publicly available LR model for immunotherapy response prediction hosted on a U.S. government website. From evaluations through its public interface, we recover the model parameters and identify the training cohort with high confidence. More broadly, we design cohort-level membership inference attacks under three levels of adversarial access---binary black-box, continuous black-box, and white-box---and apply them to both LR models and shallow neural networks (NNs) trained on the same task. Our results reveal that even a cohort of 35 patients can be reliably identified within training sets of hundreds to thousands, and that common practices such as cross-validation amplify rather than mitigate this risk. To address these vulnerabilities, we propose a quantum-inspired defense based on tensorizing discretized models into tensor trains (TTs). This representation obfuscates model parameters and preserves accuracy, while offering black-box protection comparable to practical Differential Privacy baselines. Additionally, the TT representations retain LR interpretability and extend it through efficient computation of marginal and conditional distributions, enabling this richer analysis also for black-box models such as NNs. Our results establish tensorization as a practical, post-hoc tool for private, interpretable, and effective clinical prediction.
Abstract:Publicly available clinical machine learning models pose an underappreciated privacy risk: their parameters or outputs can be exploited to recover information from patients whose data were used during training. Moreover, this risk is exacerbated by models such as logistic regression (LR), which are typically preferred in clinical settings for their transparency. To assess this empirically, we attack LORIS, a publicly available LR model for immunotherapy response prediction hosted on a U.S. government website. From evaluations through its public interface, we recover the model parameters and identify the training cohort with high confidence. More broadly, we design cohort-level membership inference attacks under three levels of adversarial access---binary black-box, continuous black-box, and white-box---and apply them to both LR models and shallow neural networks (NNs) trained on the same task. Our results reveal that even a cohort of 35 patients can be reliably identified within training sets of hundreds to thousands, and that common practices such as cross-validation amplify rather than mitigate this risk. To address these vulnerabilities, we propose a quantum-inspired defense based on tensorizing discretized models into tensor trains (TTs). This representation obfuscates model parameters and preserves accuracy, while offering black-box protection comparable to practical Differential Privacy baselines. Additionally, the TT representations retain LR interpretability and extend it through efficient computation of marginal and conditional distributions, enabling this richer analysis also for black-box models such as NNs. Our results establish tensorization as a practical, post-hoc tool for private, interpretable, and effective clinical prediction.
23 pages, 3 figures, 7 tables. The code for the experiments is publicly available at this https URL. v2: Published version. OpenReview: this https URL
Machine Learning (cs.LG); Cryptography and Security (cs.CR); Quantum Physics (quant-ph)
arXiv:2602.06110 [cs.LG]
(or arXiv:2602.06110v2 [cs.LG] for this version)
Text integral sub licența deschisă a publicației · 285 cuvinte
Subiecte conexe
Researchers Demonstrate Scalable Quantum Neural Network Training on Quantum Hardware
The Quantum Insider · 9 iun. 2026
Quantum Computing Revolutionary Promise Is Bringing Real-World Solutions
chinatechnews.com · 19 aug. 2026
News
Quantum Computing Report · 25 iul. 2026
Tensor Network Machine Learning for Wildfire Susceptibility Mapping: from Grokking Dynamics to Quantum Mixedness of Class Representations
arXiv · 23 iul. 2026