paper-with-me

홈 › Papers

The Limitations of Model Uncertainty in Adversarial Settings

2018-12-06 · Kathrin Grosse, David Pfaff, Michael Thomas Smith, Michael Backes

Machine learning models are vulnerable to adversarial examples: minor perturbations to input samples intended to deliberately cause misclassification. While an obvious security threat, adversarial examples yield as well insights about the applied model itself. We investigate adversarial examples in the context of Bayesian neural network's (BNN's) uncertainty measures. As these measures are highly non-smooth, we use a smooth Gaussian process classifier (GPC) as substitute. We show that both confidence and uncertainty can be unsuspicious even if the output is wrong. Intriguingly, we find subtle differences in the features influencing uncertainty and confidence for most tasks.

📄 PDF Abstract BibTeX arXiv:1812.02606

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningGaussian Processesmodel

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

How Wrong Am I? - Studying Adversarial Examples and their Impact on Uncertainty in Gaussian Process Machine Learning Models

2017-11-17 · Kathrin Grosse, David Pfaff, Michael Thomas Smith, Michael Backes

Machine learning models are vulnerable to Adversarial Examples: minor perturbations to input samples intended to deliberately cause misclassification. Current defenses against adversarial examples, especially for Deep Ne…

Bayesian InferenceGaussian Processes

Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification

2026-07-03 · Nicolas Sournac, Ahmed Baha Ben Jmaa, Bertrand Braeckeveldt arxiv

Safety-critical applications require classifiers that are both robust and reliable. Adversarial training is a widely adopted defense for improving robustness in deep neural networks; however, its effect on the reliabilit…

Adversarial Robustness

Multi-head Uncertainty Inference for Adversarial Attack Detection

2022-12-20 · YuQi Yang, Songyun Yang, Jiyang Xie. Zhongwei Si, Kai Guo 외

Deep neural networks (DNNs) are sensitive and susceptible to tiny perturbation by adversarial attacks which causes erroneous predictions. Various methods, including adversarial defense and uncertainty inference (UI), hav…

Adversarial AttackAdversarial Attack DetectionAdversarial Defense

Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry

2022-08-02 · Mark Penrod, Harrison Termotto, Varshini Reddy, Jiayu Yao 외

For responsible decision making in safety-critical settings, machine learning models must effectively detect and process edge-case data. Although existing works show that predictive uncertainty is useful for these tasks,…

Decision MakingDeep Learning

Uncertainty-Guided Selective Adaptation Enables Cross-Platform Predictive Fluorescence Microscopy

2025-11-15 · Kai-Wen K. Yang, Andrew Bai, Alexandra Bermudez, Yunqi Hong 외 arxiv

Deep learning is transforming microscopy, yet models often fail when applied to images from new instruments or acquisition settings. Conventional adversarial domain adaptation (ADDA) retrains entire networks, often disru…

Domain Adaptation