Jul 2026· 2026 6th International Conference on Electrical, Computer and Energy Technologies (ICECET)· pp. 1-6· 0 citations· 15 references
Abstract
This paper presents a structured and quantitative framework for evaluating the explainability of machine learning (ML) models trained on synthetic access control datasets. Explainability is assessed using four complementary metrics - stability, consistency, fidelity, and monotonicity - along with a normalized composite explainability score $E_{\text{norm}}$ that enables balanced comparison across models and datasets by addressing scale incompatibility among metrics. The framework is evaluated across four ML models (Logistic Regression, k-Nearest Neighbors, Naive Bayes, and a Neural Network) trained on six synthetic datasets ranging from rule-based and probabilistic to random and adversarial generation strategies. Results show that simpler models consistently produce more stable, consistent, and monotonic explanations on structured synthetic data, while neural networks exhibit greater variability and over-reliance on dominant features. Structured data generation methods were found to support stronger explainability than unstructured or adversarial approaches. Together, these findings provide practical guidance for selecting model-dataset combinations that support transparent and auditable decision-making in physical access control systems.
This survey highlights how optimization- and certification-oriented reasoning can provide a useful framework for reasoning about differences in models, supporting tasks ranging from model training and selection to auditing and certification.
A systematic analysis of 207 studies selected from 4447 records following the PRISMA 2020 guidelines, covering work published between 2020 and 2026 across cybersecurity and computer vision finds systems that are robust against adaptive adversaries, interpretable under operational constraints, and auditable in environments where AI accountability is a legal requirement.
Owing to the low occurrence frequencies of extreme financial risk events, risk prediction models are prone to being dominated by the majority of the normal samples encountered during the pretraining process when using financial risk data. This weakens the ability to effectively learn abnormal characteristics and thus reduces the sensitivity and stability of the developed predictive model. To overcome these limitations, a data class-balancing model, Financial Wasserstein Generative Adversarial Network with Gradient Penalty (FinWGAN-GP), is constructed on the basis of the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) framework. Experimental results reveal that the FinWGAN-GP model achieves high-fidelity generation and expansion for high-risk samples, and a balanced dataset is conducive to improving the training effect of the early warning model. Through the integration of multisource heterogeneous data and Artificial Intelligence (AI) methods, the proposed model can identify potential financial risks earlier and more accurately, helping enhance the forward-looking and scientific nature of financial regulation.
Bo Xu, Lifei Lu, Yulin Lu et al.· Journal of Fintech and Busin...· 0 citations
Diffusion Language Models (DLMs) offer a compelling alternative to autoregressive (AR) generation by enabling bidirectional context and iterative refinement. However, their reliability under natural input noise and adversarial attacks remains under-explored. To address this, we systematically evaluate DLM robustness and calibration against AR baselines, using two parameter-matched pairs (LLaDA-8B vs. LLaMA-3-8B and Dream-7B vs. Qwen2.5-7B) across 32 natural perturbation conditions, adversarial gradient probes, and mechanistic hidden-state analyses. This paired design effectively isolates architecture-intrinsic properties from weight-dependent behaviors. We find a nuanced robustness profile: while highly stochastic DLM loss landscapes naturally resist gradient-based adversarial suffixes, they provide no guaranteed defense against natural noise, proving that everyday robustness is weight-dependent rather than inherently architectural. Furthermore, DLMs exhibit systematic overconfidence, presenting a practical deployment hazard. Most crucially, mechanistic probing reveals that all models perfectly encode input corruption, isolating behavioral fragility entirely to a decoder routing failure. Consistent with this diagnosis, we show that surface-level prompt patching fails to improve over noisy baselines. Ultimately, DLM robustness cannot be patched on; it must be fundamentally integrated into the iterative decoding loop.
Saurabh Yadav, B. N. Patro, V. Agneeswaran· 0 citations
This paper presents a systematic framework for membership inference attacks, in which an adversary with only black-box query access to a deployed classifier determines whether a specific individual's record was part of its training set.
Pramod Prakash· International Journal of Int...· 0 citations
The sharing of patient-level structured data is strictly constrained by privacy regulations and governance, creating “data silos” that hinder multi-center research. We propose the CLEO (Clean-Learn-Evaluate-Optimize), a closed-loop framework that integrates a Gaussian Mixture Model generator with Q-learning-based optimization to formalize data synthesis as a Markov Decision Process. Experimental results on a multicenter intracranial aneurysm dataset show that CLEO achieved a combined score of 0.9232 ± 0.0124, outperforming the evaluated representative comparison methods, including TVAE, Gaussian Copula, and CTGAN. In downstream TSTR evaluation, models trained on CLEO-generated data achieved an average AUC of 0.7376, indicating that the synthetic data retained useful clinical decision signals. However, Macro-F1 results also suggest that minority-class prediction remains affected by the imbalanced class distribution. Empirical privacy auditing showed a Nearest Neighbor Adversarial Accuracy score of 0.4940, suggesting low observed re-identification risk under the adopted nearest-neighbor audit setting. These findings indicate that CLEO provides a controllable and empirically auditable framework for supporting cross-institutional research when real-world medical data cannot be directly aggregated.
Siqi Wang, Jianfeng Wang, Xiaochun Cheng et al.· npj Digital Medicine· 0 citations