# TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural Networks

Source: [TriQDef: Disrupting Semantic and Gradient Alignment to Prevent Adversarial Patch Transferability in Quantized Neural Networks](<https://www.sota2.com/research/paper/68fa7aa71e209131cea846ab>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:24:53.663Z

Authors: Amira Guesmi, Bassem Ouni, Muhammad Shafique

Published: 2025-08-16T18:51:48.000Z

## Abstract

Quantized Neural Networks (QNNs) are increasingly deployed in edge and resource-constrained environments due to their efficiency in computation and memory usage. While shown to distort the gradient landscape and weaken conventional pixel-level attacks, it provides limited robustness against patch-based adversarial attacks-localized, high-saliency perturbations that remain surprisingly transferable across bit-widths. Existing defenses either overfit to fixed quantization settings or fail to address this cross-bit generalization vulnerability. We introduce \\textbf{TriQDef}, a tri-level quantization-aware defense framework designed to disrupt the transferability of patch-based adversarial attacks across QNNs. TriQDef consists of: (1) a Feature Disalignment Penalty (FDP) that enforces semantic inconsistency by penalizing perceptual similarity in intermediate representations; (2) a Gradient Perceptual Dissonance Penalty (GPDP) that explicitly misaligns input gradients across bit-widths by minimizing structural and directional agreement via Edge IoU and HOG Cosine metrics; and (3) a Joint Quantization-Aware Training Protocol that unifies these penalties within a shared-weight training scheme across multiple quantization levels. Extensive experiments on CIFAR-10 and ImageNet demonstrate that TriQDef reduces Attack Success Rates (ASR) by over 40\\% on unseen patch and quantization combinations, while preserving high clean accuracy. Our findings underscore the importance of disrupting both semantic and perceptual gradient alignment to mitigate patch transferability in QNNs.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.12132>)

[PDF](<https://arxiv.org/pdf/2508.12132.pdf>)
