Quantifying Adversarial Uncertainty in Evidential Deep Learning using Conflict Resolution

2025-06-06

AI Summary

Deep learning models often produce overconfident yet incorrect predictions on out-of-distribution (OOD) or adversarial inputs, undermining reliability in safety-critical applications. To address the overconfidence of evidential deep learning (EDL) under input perturbations, we propose C-EDL—a lightweight, post-hoc uncertainty calibration framework. Its core innovation is a representation conflict-aware calibration mechanism: leveraging task-preserving input transformations to extract feature-level conflict signals, and integrating them into Dirichlet-distributed evidence modeling—enabling dynamic confidence recalibration without model retraining. Experiments across multiple datasets and attack types demonstrate that C-EDL significantly improves uncertainty quantification quality: OOD detection coverage decreases by 55%, adversarial coverage drops by 90%, while in-distribution accuracy remains stable. C-EDL consistently outperforms existing EDL variants and mainstream baselines in comprehensive uncertainty-aware evaluation metrics.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Adversarial Attacks & Robustness
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Reliability of deep learning models is critical for deployment in high-stakes applications, where out-of-distribution or adversarial inputs may lead to detrimental outcomes. Evidential Deep Learning, an efficient paradigm for uncertainty quantification, models predictions as Dirichlet distributions of a single forward pass. However, EDL is particularly vulnerable to adversarially perturbed inputs, making overconfident errors. Conflict-aware Evidential Deep Learning (C-EDL) is a lightweight post-hoc uncertainty quantification approach that mitigates these issues, enhancing adversarial and OOD robustness without retraining. C-EDL generates diverse, task-preserving transformations per input and quantifies representational disagreement to calibrate uncertainty estimates when needed. C-EDL's conflict-aware prediction adjustment improves detection of OOD and adversarial inputs, maintaining high in-distribution accuracy and low computational overhead. Our experimental evaluation shows that C-EDL significantly outperforms state-of-the-art EDL variants and competitive baselines, achieving substantial reductions in coverage for OOD data (up to 55%) and adversarial data (up to 90%), across a range of datasets, attack types, and uncertainty metrics.

Problem

• Improves adversarial uncertainty quantification in Evidential Deep Learning
• Enhances robustness against out-of-distribution and adversarial inputs
• Reduces overconfident errors without retraining the model

Innovation

• Conflict-aware Evidential Deep Learning (C-EDL) approach
• Generates diverse task-preserving input transformations
• Quantifies representational disagreement for uncertainty calibration