Proposes a new trust framework for AI models to maximize utility.
problem Concerns over bias and discrimination in predictive models.
method Introduces a novel trust framework inspired by philosophy, focusing on maximizing Bayes utility.
result Properly-ranked models are inherently U-trustworthy. AI systems need reliable testing to ensure safety and trustworthiness.
problem Current AI Act lacks functional trustworthiness for AI systems.
method Define technical application distribution, set risk-based performance, and conduct statistically valid testing.
result Reliable functional trustworthiness is essential for AI systems.
Survey reviews explainability in AI for healthcare, emphasizing trust and transparency.
problem Lack of transparency hinders AI adoption in healthcare.
method Comprehensive literature review to guide explainable AI design.
result Quantitative evaluation metrics are needed for some explainability properties.
Research tackles distribution shift issues in ML to improve AI reliability.
problem Distribution shift limits ML reliability and trustworthiness.
method Study three distribution shifts (perturbation, domain, modality) and investigate robustness, explainability, adaptability.
result Proposes effective solutions and fundamental insights for enhancing ML robustness, adaptability, and safety.
Neural approach enhances AI trustworthiness, generalization, and robustness.
problem Challenges in explaining, generalizing, and adapting AI models to uncertain environments.
method Customized trustworthy networks, flexible learning regularizers, open-world recognition losses.
result Significant performance improvements across various open-world multimedia recognition scenarios.
This paper introduces Probability Engineering to improve deep learning models.
problem Challenges in traditional probabilistic modeling for AI applications.
method Treats learned probability distributions as engineering artifacts and actively modifies them.
result Improves robustness, efficiency, adaptability, and trustworthiness of deep learning models.
Framework audits synthetic datasets for trustworthiness across various use cases.
problem Assessing the trustworthiness of synthetic datasets and models.
method Holistic auditing framework focusing on bias, fidelity, utility, robustness, and privacy.
result Introduces a trustworthiness index and model selection process for controllable trade-offs.
Develops methods for AI self-assessment to improve trustworthiness.
problem Uncertainty in AI predictions and lack of trust in AI systems.
method Uncertainty estimation techniques considering practical impacts and costs.
result Guidelines for selecting and designing effective AI self-assessment methods.
Survey of technologies for trustworthy machine learning systems.
problem Building machine learning systems that are fair, explainable, auditable, and secure.
method Survey of technologies across data and model stages of machine learning.
result Four categories of system properties (fairness, explainability, auditability, safety & security) are essential for trustworthy systems.
PiNets provide faithful explanations for neural networks.
problem Lack of true explanations for neural network predictions.
method Pointwise-interpretable Networks (PiNets) that form linear models instance-wise.
result PiNets offer explanations that are meaningful, aligned, robust, and sufficient.
The paper introduces logic constraints to improve AI model interpretability.
problem The black box nature of AI models limits their trustworthiness in high-stakes fields.
method The paper extends AI models with logic constraints to make feature importance more interpretable.
result Promising experimental results have been achieved for the Adult dataset.
FreB protocol uses AI to infer hidden parameters with valid confidence regions.
problem Generating biased or overconfident conclusions from AI-generated posterior distributions.
method Frequentist-Bayes (FreB) protocol reshapes AI-generated posterior distributions into valid confidence regions.
result FreB provides valid confidence regions that consistently include true parameters with expected probability.
DeFi TrustBoost uses blockchain and AI to assess small business loans.
problem Assessing small business loans from low-wealth households.
method Combines blockchain and Explainable AI to ensure confidentiality, compliance, and security.
result Tamper-proof auditing and on-chain/off-chain data storage for financial organizations.
AI needs causal inference to avoid being just a correlation machine.
problem AI's inability to distinguish correlation from causation.
method Develops a unified framework connecting various causal statistical estimators and proves a Statistical Necessity Theorem for causal generalization.
result AI systems without causal grounding are brittle and biased, highlighting the need for causal statistics.
Paper tackles selective regression using uncertainty estimation.
problem Selective regression for machine learning models to avoid predictions when uncertain.
method Model-agnostic non-parametric uncertainty estimation.
result Superior performance compared to state-of-the-art selective regressors.
Efficient approach improves prediction calibration for domain shifts.
problem Improving uncertainty-aware predictions for domain shifts.
method Combining entropy-encouraging and adversarial calibration losses.
result Substantially outperforms existing approaches in domain drift calibration.
FST.ai 2.0 improves Taekwondo decision-making with AI, reducing review time and increasing trust.
problem Fair, transparent, and explainable decision-making in Taekwondo.
method Pose-based action recognition, epistemic uncertainty modeling, interactive dashboards.
result 85% reduction in decision review time, 93% referee trust in AI-assisted decisions.
Do-AIQ framework evaluates AI algorithms' quality using DOE.
problem Quality evaluation of AI mislabel detection algorithms.
method Design-of-experiment approach with high-dimensional constraint space design and surrogate modeling.
result Established framework for evaluating AI algorithm quality robustly.
Paper investigates monotonicity issues in AI preference learning.
problem AI models may violate monotonicity when learning preferences.
method Investigates root causes of non-monotonicity in comparison-based preference learning.
result Proves local pairwise monotonicity under mild assumptions.
AI helps HEP measure uncertainties, but needs better interpretation.
problem Uncertainty interpretation in AI for HEP measurements.
method Discussing existing AI methods for inference, simulation, and control/decision-making.
result Need for trustworthy AI UQ methods for widespread usage.
Unified AI system for data quality control and governance in regulated environments.
problem Isolated data quality control steps in existing systems.
method AI-driven framework integrating rule-based, statistical, and AI methods.
result Empirical gains in anomaly detection, reduced manual remediation, improved auditability.
VERAFI improves financial AI by verifying calculations and compliance.
problem Financial AI systems generate errors and violations during reasoning.
method VERAFI combines dense retrieval, reranking, and automated reasoning policies.
result VERAFI achieves 94.7% factual correctness, 81% relative improvement.
A new score function improves explainability and reliability of AI systems.
problem Designing AI systems that are explainable, robust, and trustworthy.
method Integrates conformal prediction with explainable machine learning using a novel score function.
result The method achieves improved performance on target classes and satisfies conformal guarantees.
Blockchain helps secure payments between AI agents.
problem Ensuring secure payments between untrusted AI agents.
method Systematized four-stage lifecycle for A2A payments on blockchain.
result Challenges remain in weak intent binding, misuse, and limited accountability.
Enhances out-of-domain calibration of neural networks.
problem Improving calibration performance of deep neural networks in out-of-domain settings.
method Consistency-guided temperature scaling (CTS) that considers style and content consistency.
result Significantly enhances out-of-domain calibration performance.
New calibration measure SCDL improves trust in AI predictions.
problem Improving trust in AI predictions by ensuring they are both actionable and testable.
method Introducing SCDL, a new calibration measure that is fully actionable and testable.
result SCDL is the first calibration measure that is fully actionable and testable.
Proposes a sample selection algorithm for fair and robust AI training.
problem Balancing fairness and robustness in AI models, especially with corrupted data.
method Formulates and solves a combinatorial optimization problem for unbiased sample selection, proposing a greedy algorithm.
result Improves fairness and robustness compared to state-of-the-art techniques, both synthetically and on real datasets.
LPF provides formal guarantees for aggregating multi-evidence in probabilistic tasks.
problem Lack of formal guarantees for multi-evidence reasoning in AI.
method LPF uses variational autoencoders and Sum-Product Networks to aggregate evidence items.
result Proves multiple formal guarantees including calibration preservation and error decay.
Rubin LSST DESC uses AI/ML for dark energy research.
problem Challenges in uncertainty quantification and model robustness for AI/ML in DESC.
method Bayesian inference, physics-informed methods, validation frameworks, active learning.
result AI/ML methods are essential but require rigorous evaluation and governance.
Statisticians contribute to LLMs for better trust and transparency.
problem Emerging statistical challenges in LLMs.
method Exploring statistical contributions to LLMs.
result Statisticians can enhance LLMs' trustworthiness and transparency.
A framework assesses the trustworthiness of probabilistic classifiers using local calibration error.
problem Assessing the trustworthiness of probabilistic classifiers beyond traditional metrics.
method I-trustworthy framework linking local calibration to trustworthiness; Kernel Local Calibration Error (KLCE) method for hypothesis testing.
result The effectiveness of the proposed test statistic demonstrated through simulated and real-world datasets.
Hybrid AI and rule-based framework de-identifies medical imaging data.
problem De-identifying medical imaging data to protect PHI and PII.
method Combines rule-based and AI techniques with uncertainty quantification.
result Robust performance across benchmark datasets and regulatory standards.
Study benchmarks uncertainty quantification in chest X-ray classification.
problem Reliable uncertainty quantification for medical AI models.
method Evaluation of 13 uncertainty quantification methods on MIMIC-CXR-JPG dataset.
result Insights into effectiveness and disentanglement of epistemic and aleatoric uncertainties.
We demonstrate how easy it is for modern machine-learned systems to violate common deontological ethical principles and social norms such as "favor the less fortunate," and "do not penalize good attributes." We propose that in some cases such ethical principles can be incorporated into a machine-learned model by adding…
New metric assesses reliability of AI explanations.
problem Unreliable AI explanations under realistic conditions.
method Explanation Reliability Index (ERI) metrics quantifying stability under four axioms.
result Widespread reliability failures in popular explanation methods.
Blockchain aims to improve trust in AI systems, but lacks systematic studies.
problem Lack of systematic studies on blockchain design principles for AI trust.
method Hybrid qualitative and quantitative studies.
result Vast opportunities for future research and practice in blockchain design.
RESTA defends LLMs against jailbreaking attacks by adding random noise to embeddings.
problem Vulnerability of LLMs to jailbreaking attacks that generate harmful outputs.
method Adds random noise to embedding vectors and aggregates during token generation.
result RESTA achieves superior robustness versus utility tradeoffs compared to baseline defenses.
FR-Train improves fair and robust AI training by detecting and reducing poisoned data.
problem Training AI models that are fair and robust in the presence of data bias and poisoning.
method Mutual information-based adversarial training with an additional discriminator.
result FR-Train maintains fairness and accuracy even in the presence of poisoned data.
Improved credit scoring model with explainability.
problem Making financial decisions based on loan applications.
method Extreme Gradient Boosting (XGBoost) model with 360-degree explanation framework.
result Model achieves state-of-the-art performance and provides understandable explanations.
This paper explores how balancing and filtering techniques affect predictive multiplicity in machine learning models.
problem Predictive multiplicity due to Rashomon effect in high-stakes environments.
method Investigates the impact of balancing and filtering techniques on predictive multiplicity using 21 real-world datasets.
result Data-centric AI strategies can mitigate predictive multiplicity, but preprocessing methods may introduce it.
Topological parallax assesses AI models' geometric similarity to datasets for safety.
problem Ensuring AI models' robustness and safety in deep learning applications.
method Topological parallax compares a trained model to a reference dataset using Rips complexes and geodesic distortions.
result Topological parallax indicates whether a model shares similar multiscale geometric features with the dataset.
Bayesian meta learning improves uncertainty quantification in regression.
problem Trusting uncertainty quantification in Bayesian regression.
method Trust-Bayes framework for Bayesian meta learning, optimizing for trustworthy uncertainty quantification.
result Lower bounds and sample complexity for trustworthy uncertainty quantification are characterized.
Proposes new loss functions for better handling bimodal predictive uncertainty.
problem Bimodal predictive uncertainty in machine learning models.
method Family of distribution-aware loss functions integrating normalized RMSE with Wasserstein and Cramér distances.
result Proposed loss functions reduce predictive uncertainty estimation error by 45% on complex bimodal datasets.
A new metric MSD detects bias in datasets efficiently.
problem Detecting bias in AI systems and datasets.
method Introduced Maximum Subgroup Discrepancy (MSD) metric and a practical algorithm based on MIO.
result MSD provides a linear sample complexity for practical applications, distinguishing biases effectively.
Objective: To determine the completeness of argumentative steps necessary to conclude effectiveness of an algorithm in a sample of current ML/AI supervised learning literature. Data Sources: Papers published in the Neural Information Processing Systems (NeurIPS, née NIPS) journal where the official record showed a 2017…
Bayesian framework improves ML classification models' uncertainty estimates.
problem Ensuring trustworthy AI predictions with explicit uncertainty quantification.
method Proposes a Bayesian framework for generative ML classification models that accounts for input measurement uncertainty.
result The BQDA model outperforms other models in terms of interpretability, explicit uncertainty modeling, and computational efficiency.
ExCIR provides efficient, consistent, and scalable explainability for complex models.
problem Complex models lack transparency and require efficient, stable, and scalable explainability methods.
method ExCIR uses correlation-aware feature attribution with robust centering and groupwise aggregation.
result ExCIR delivers trustworthy agreement with global baselines and full model rankings, reduces runtime, and scales to large datasets.
Glitches cause unreliable AI decisions with steep boundaries.
problem Glitches impair the reliability of AI models with steep decision boundaries.
method Formal definition of glitches, algorithmic search using MILP encoding.
result Glitches are widespread and indicate potential model inconsistencies.