LGAIMLJun 9, 2025

Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability

arXiv:2506.07804v17 citationsh-index: 7Has CodeICML
Originality Incremental advance
AI Analysis

This work addresses the need for reliable and resilient models in safety-critical domains, representing an incremental improvement by combining existing techniques in a novel way.

The paper tackles the problem of adversarial robustness in deep learning by integrating conformal prediction into adversarial training, resulting in a defense method (OPSA-AT) that significantly enhances robustness against various attacks while maintaining reliable predictions.

As deep learning models are increasingly deployed in high-risk applications, robust defenses against adversarial attacks and reliable performance guarantees become paramount. Moreover, accuracy alone does not provide sufficient assurance or reliable uncertainty estimates for these models. This study advances adversarial training by leveraging principles from Conformal Prediction. Specifically, we develop an adversarial attack method, termed OPSA (OPtimal Size Attack), designed to reduce the efficiency of conformal prediction at any significance level by maximizing model uncertainty without requiring coverage guarantees. Correspondingly, we introduce OPSA-AT (Adversarial Training), a defense strategy that integrates OPSA within a novel conformal training paradigm. Experimental evaluations demonstrate that our OPSA attack method induces greater uncertainty compared to baseline approaches for various defenses. Conversely, our OPSA-AT defensive model significantly enhances robustness not only against OPSA but also other adversarial attacks, and maintains reliable prediction. Our findings highlight the effectiveness of this integrated approach for developing trustworthy and resilient deep learning models for safety-critical domains. Our code is available at https://github.com/bjbbbb/Enhancing-Adversarial-Robustness-with-Conformal-Prediction.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes