Conformal Alignment ensures trustworthy outputs from foundation models.
problem Ensuring outputs from foundation models align with human values in high-stakes tasks.
method A framework that trains an alignment predictor using reference data to select trustworthy outputs.
result Conformal Alignment accurately identifies trustworthy outputs via lightweight training over moderate reference data.
Consensus dimension reduction combines multiple visualizations to identify shared patterns.
problem Conflicting visualizations from different dimension reduction methods.
method Multi-view learning to identify stable patterns across multiple views.
result Consensus visualization effectively identifies shared low-dimensional data structure.
Paper monitors DNN accuracy to enhance trustworthiness.
problem Varying DNN accuracy in practice and lack of ground truth labels.
method Post-hoc accuracy monitor model using Monte-Carlo dropout ensemble.
result Accuracy monitor provides close-to-true accuracy estimation.
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. This work improves neural network trustworthiness through uncertainty estimation.
problem Overconfident neural networks lead to poor performance under distribution shifts.
method Develops a general uncertainty framework for neural networks, including classification with rejection.
result Improves model trustworthiness and robustness in decision-making tasks.
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.
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.
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.
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.
Paper introduces conformal prediction for reliable uncertainty quantification in landmark localization.
problem Systematic underestimation of total predictive uncertainty in landmark localization.
method Conformal prediction framework for multi-output regression, generating flexible prediction regions.
result Methods outperform existing approaches in validity and efficiency across 2D and 3D datasets.
Explanation methods aim to make neural networks more trustworthy and interpretable. In this paper, we demonstrate a property of explanation methods which is disconcerting for both of these purposes. Namely, we show that explanations can be manipulated arbitrarily by applying visually hardly perceptible perturbations to…
Online knowledge repositories typically rely on their users or dedicated editors to evaluate the reliability of their content. These evaluations can be viewed as noisy measurements of both information reliability and information source trustworthiness. Can we leverage these noisy evaluations, often biased, to distill a…
ManifoldMind uses adaptive-curvature probabilistic spheres for trustworthy recommendations in semantic hierarchies.
problem Sparse and abstract recommendation domains where users explore diverse conceptual paths.
method Adaptive-curvature probabilistic spheres, soft multi-hop inference, and curvature-aware semantic kernel.
result Superior NDCG, calibration, and diversity compared to baselines on public benchmarks.
A framework for analyzing regularizers to ensure trustworthy theory-driven model estimation.
problem Uncertain choice of regularizers can compromise the interpretability of deep grey-box models.
method Adapting neural net architecture and training objective to analyze regularizer behavior empirically.
result Empirical analysis of regularizers helps in making a justified choice for trustworthy theory-driven model estimation.
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.
This work introduces RISE to explain LLMs more reliably by distinguishing essential context.
problem Identifying which context elements influence LLM outputs reliably.
method RISE (Redundancy-Insensitive Scoring of Explanation) method.
result RISE provides more robust explanations than traditional methods.
New research finds tree-based GAMs are most trustworthy and fair.
problem Variability in GAM algorithms leads to inconsistent models.
method Quantitative and qualitative analysis of various GAM algorithms.
result Tree-based GAMs are the most trustworthy and fair.
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.
In the context of fake news, bias, and propaganda, we study two important but relatively under-explored problems: (i) trustworthiness estimation (on a 3-point scale) and (ii) political ideology detection (left/right bias on a 7-point scale) of entire news outlets, as opposed to evaluating individual articles. In partic…
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.
Proposes a game-theoretic framework for ML trust regulation.
problem Lack of coordination between ML model builders and regulators.
method Formulates trustworthy ML as a multi-objective multi-agent optimization problem and introduces regulation games and ParetoPlay.
result Enables efficient enforcement of ML model specifications without discouraging participation.
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.
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.
Study shows trust and trustworthiness emerge through reinforcement learning.
problem Trust and trustworthiness are universal but not predicted by traditional economic models.
method Used Q-learning algorithm to simulate trust and trustworthiness dynamics in a trust game.
result High levels of trust and trustworthiness emerge when individuals consider both past and future experiences.
Enhanced conformal methods improve validity of LLM outputs.
problem Lack of conditional validity and high false rejection rates in LLM validity guarantees.
method Adaptive conditional conformal procedure and improved scoring function differentiation.
result Demonstrated improved validity and utility on real datasets.
Researchers develop methods to prevent GANs from generating certain types of images.
problem Pre-trained GANs sometimes produce undesirable samples.
method Post-editing GANs to prevent certain types of outputs, using three algorithms.
result Our algorithms effectively prevent GANs from generating certain types of images while maintaining high quality.
While social networks can provide an ideal platform for up-to-date information from individuals across the world, it has also proved to be a place where rumours fester and accidental or deliberate misinformation often emerges. In this article, we aim to support the task of making sense from social media data, and speci…
Online health communities are a valuable source of information for patients and physicians. However, such user-generated resources are often plagued by inaccuracies and misinformation. In this work we propose a method for automatically establishing the credibility of user-generated medical statements and the trustworth…
An emerging problem in trustworthy machine learning is to train models that produce robust interpretations for their predictions. We take a step towards solving this problem through the lens of axiomatic attribution of neural networks. Our theory is grounded in the recent work, Integrated Gradients (IG), in axiomatical…
PACE explains ViTs by modeling patch-level concept distributions, surpassing existing methods.
problem Lack of trustworthy post-hoc explanations for Vision Transformers (ViTs)
method Variational Bayesian explanation framework (PACE)
result PACE surpasses state-of-the-art methods in meeting desiderata for ViT explanations.
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.
Study on stability of GCNNs under graph perturbations.
problem Limited theoretical understanding of GCNN stability.
method Proposes a probabilistic framework to analyze GCNN stability under various graph perturbations.
result Demonstrates the importance of data distribution in stability analysis.
Paper explores differential privacy in high-dimensional federated learning, tackling server trustworthiness and estimation.
problem Maintaining privacy in distributed environments with high-dimensional data.
method Investigates scenarios with untrusted and trusted central servers, introduces novel federated estimation algorithms for linear regression models.
result Tight minimax rates depend on high-dimensionality even with sparsity assumptions, and novel algorithms handle slight variations among distributed models.
User strategization undermines algorithmic trustworthiness.
problem User strategic behavior corrupts algorithmic data and trust.
method Modeling user-platform interactions as a game, analyzing strategic behavior's short-term benefits and long-term harms.
result User strategization can initially benefit platforms but ultimately harms their ability to make accurate decisions.
Paper uses PCE to quantify ML model and input uncertainties.
problem Accurately quantify and propagate combined uncertainties in ML predictions.
method Polynomial Chaos Expansion (PCE) for joint input and model uncertainty.
result Efficient and accurate calculation of output variability and sensitivity.
Stabilizing black-box algorithms through task-oriented randomization
problem Ensuring stability of black-box models
method Task-oriented randomization
result Established rigorous theoretical foundations and demonstrated effectiveness through simulations and real-world applications
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.
Study improves summarization reliability in risky scenarios.
problem Reliability of automatic summarization in high-risk contexts.
method Conditional generation with Bayesian inference and entropy regularization.
result Significant improvement in robustness and reliability of summarization.
New method tackles label noise on imbalanced datasets by considering class-specific uncertainty.
problem Label noise and class imbalance in imbalanced datasets.
method Epistemic and aleatoric uncertainty-aware class-specific noise modeling.
result Proposed ULC framework improves performance on imbalanced datasets.
Diverging Flows detects extrapolations in flow models, ensuring reliable predictions.
problem Flow models extrapolate into invalid data, leading to silent failures.
method Structurally enforce inefficient transport for off-manifold inputs.
result Effective detection of extrapolations without compromising predictive fidelity or inference latency.
Conformal prediction improves signal detection accuracy in railway images.
problem Improving the reliability of machine learning models for railway signal detection.
method Applying conformal prediction to a novel dataset of train operator perspective images.
result The approach enhances the reliability of machine learning models for detecting railway signals.
DS-CP improves reliability of uncertainty quantification for large language models under domain shift.
problem Overconfident and factually incorrect outputs (hallucinations) from large language models.
method Adapts conformal prediction to large language models under domain shift by reweighting calibration samples.
result DS-CP delivers more reliable coverage than standard conformal prediction, especially under substantial distribution shifts.
TaylorPODA uses Taylor expansions to improve feature attributions for opaque models.
problem Lack of systematic framework for quantifying feature contributions in opaque models.
method Taylor expansion framework with postulates (precision, federation, zero-discrepancy, adaptation).
result TaylorPODA achieves competitive results and provides principled explanations.
New holistic approach measures sample-level adversarial vulnerability for trustworthy systems.
problem Inherent bias in adversarial attacks across subgroups.
method Combining high-frequency feature reliance and sample-distance to decision boundary.
result Holistic approach improves adversarial vulnerability estimation and system trustworthiness.
Paper quarantines unreliable Yelp users by detecting review spam.
problem Unreliable and spamming users deceive Yelp's users.
method Used RSD and spam detection techniques on key features.
result More than 80% of Yelp's accounts are unreliable, and highly-rated businesses are often spammed.
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.
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.
In many contexts, it can be useful for domain experts to understand to what extent predictions made by a machine learning model can be trusted. In particular, estimates of trustworthiness can be useful for fraud analysts who process machine learning-generated alerts of fraudulent transactions. In this work, we present …