paper-with-me

홈 › Papers

Trust Regions for Explanations via Black-Box Probabilistic Certification

2024-02-17 · Amit Dhurandhar, Swagatam Haldar, Dennis Wei, Karthikeyan Natesan Ramamurthy

Given the black box nature of machine learning models, a plethora of explainability methods have been developed to decipher the factors behind individual decisions. In this paper, we introduce a novel problem of black box (probabilistic) explanation certification. We ask the question: Given a black box model with only query access, an explanation for an example and a quality metric (viz. fidelity, stability), can we find the largest hypercube (i.e., $\ell_{\infty}$ ball) centered at the example such that when the explanation is applied to all examples within the hypercube, (with high probability) a quality criterion is met (viz. fidelity greater than some value)? Being able to efficiently find such a \emph{trust region} has multiple benefits: i) insight into model behavior in a \emph{region}, with a \emph{guarantee}; ii) ascertained \emph{stability} of the explanation; iii) \emph{explanation reuse}, which can save time, energy and money by not having to find explanations for every example; and iv) a possible \emph{meta-metric} to compare explanation methods. Our contributions include formalizing this problem, proposing solutions, providing theoretical guarantees for these solutions that are computable, and experimentally showing their efficacy on synthetic and real data.

📄 PDF Abstract BibTeX arXiv:2402.11168

Code (1)

Trusted-AI/AIX360 공식 구현 pytorch

Similar Papers 제목 키워드 기반

"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations

2019-11-15 · Himabindu Lakkaraju, Osbert Bastani

As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on developing techniques for explaining these black boxes in …

The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis

2024-07-22 · Benjamin Fresz, Vincent Philipp Göbels, Safa Omri, Danilo Brajovic 외

Developing and certifying safe - or so-called trustworthy - AI has become an increasingly salient issue, especially in light of upcoming regulation such as the EU AI Act. In this context, the black-box nature of machine …

LaPLACE: Probabilistic Local Model-Agnostic Causal Explanations

2023-10-01 · Sein Minn

Machine learning models have undeniably achieved impressive performance across a range of applications. However, their often perceived black-box nature, and lack of transparency in decision-making, have raised concerns a…

Decision MakingFairnessmodelModel Selection

Trustworthy Visual Analytics in Clinical Gait Analysis: A Case Study for Patients with Cerebral Palsy

2022-08-10 · Alexander Rind, Djordje Slijepčević, Matthias Zeppelzauer, Fabian Unglaube 외

Three-dimensional clinical gait analysis is essential for selecting optimal treatment interventions for patients with cerebral palsy (CP), but generates a large amount of time series data. For the automated analysis of t…

ClassificationExplainable artificial intelligenceTime SeriesTime Series Analysis

Bayesian Safety Validation for Failure Probability Estimation of Black-Box Systems

2023-05-03 · Robert J. Moss, Mykel J. Kochenderfer, Maxime Gariel, Arthur Dubois

Estimating the probability of failure is an important step in the certification of safety-critical systems. Efficient estimation methods are often needed due to the challenges posed by high-dimensional input spaces, risk…

Bayesian OptimizationDecision Making