A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Reality

TL;DR

This paper presents CADAR, a neuro-symbolic framework combining neural and symbolic reasoning to detect cognitive attacks in augmented reality, enhancing interpretability and robustness over existing visual-only methods.

Contribution

The paper introduces CADAR, a novel neuro-symbolic approach that integrates multimodal perception graphs with probabilistic reasoning for semantic attack detection in AR.

Findings

CADAR outperforms existing methods on AR attack datasets.

The framework provides interpretable insights into semantic anomalies.

Preliminary results show improved detection accuracy and robustness.

Abstract

Augmented Reality (AR) enriches human perception by overlaying virtual elements onto the physical world. However, this tight coupling between virtual and real content makes AR vulnerable to cognitive attacks: manipulations that distort users' semantic understanding of the environment. Existing detection methods largely focus on visual inconsistencies at the pixel or image level, offering limited semantic reasoning or interpretability. To address these limitations, we introduce CADAR, a neuro-symbolic framework for cognitive attack detection in AR that integrates neural and symbolic reasoning. CADAR fuses multimodal vision-language representations from pre-trained models into a perception graph that captures objects, relations, and temporal contextual salience. Building on this structure, a particle-filter-based statistical reasoning module infers anomalies in semantic dynamics to reveal cognitive attacks. This combination provides both the adaptability of modern vision-language models and the interpretability of probabilistic symbolic reasoning. Preliminary experiments on an AR cognitive-attack dataset demonstrate consistent advantages over existing approaches, highlighting the potential of neuro-symbolic methods for robust and interpretable AR security.