Streaming Adversarial Robustness in Fuzzy ARTMAP: Mechanism-Aligned Evaluation, Progressive Training, and Interpretable Diagnostics

TL;DR

This paper investigates adversarial robustness in streaming neural learners, specifically Fuzzy ARTMAP, introducing a new attack method, WB-Softmax, and evaluating robustness with a protocol-aware framework across image benchmarks.

Contribution

It introduces WB-Softmax, a white-box attack aligned with Fuzzy ARTMAP's mechanisms, and proposes a streaming evaluation principle for robustness assessment.

Findings

WB-Softmax achieves 89-100% attack success on vanilla Fuzzy ARTMAP models.

Defense rankings vary across protocols; offline training may not be effective under adaptive attacks.

Progressive two-stage training offers the strongest replay-free robustness.

Abstract

Adversarial robustness has been studied extensively for offline deep networks, but less is known about strict single-pass streaming neural learners. This paper studies adversarial robustness in Fuzzy ARTMAP, an Adaptive Resonance Theory architecture based on category competition, complement coding, match tracking, and replay-free prototype updates. We introduce WB-Softmax, a differentiable white-box attack surrogate aligned with ARTMAP's category-competition and map-field prediction mechanism, and formalize a streaming evaluation principle requiring robustness to be assessed on the final deployed model. Across four image benchmarks, WB-Softmax achieves 89-100% attack success on vanilla Fuzzy ARTMAP models. We show that defense rankings can reverse across protocols: offline adversarial training may appear strong under transfer attacks yet collapse under adaptive white-box evaluation, whereas progressive two-stage selective training provides the strongest overall replay-free robustness. We further show that ART's explicit category geometry enables interpretable diagnosis of separation collapse and match-score inversion. These results provide a mechanism-aligned, protocol-aware framework for adversarial robustness in streaming prototype-based learners.