MeetSafe: enhancing robustness against white-box adversarial examples

: Stenhuis, Ruben; Liu, Dazhuang; Qiao, Yanqi; Conti, Mauro; Panaousis, Manos; Liang, Kaitai

Publisher: Frontiers Media SA

: 2025

Frontiers in Computer Science

: 1631561

: 7

: 2624-9898

DOI: https://doi.org/10.3389/fcomp.2025.1631561

: https://doi.org/10.3389/fcomp.2025.1631561

Convolutional neural networks (CNNs) are vulnerable to adversarial attacks in computer vision tasks. Current adversarial detections are ineffective against white-box attacks and inefficient when deep CNNs generate high-dimensional hidden features. This study proposes MeetSafe, an effective and scalable adversarial example (AE) detection against white-box attacks. MeetSafe identifies AEs using critical hidden features rather than the entire feature space. We observe a non-uniform distribution of Z-scores between clean samples and adversarial examples (AEs) among hidden features and propose two utility functions to select those most relevant to AEs. We process critical hidden features using feature engineering methods: local outlier factor (LOF), feature squeezing, and whitening, which estimate feature density relative to its k-neighbors, reduce redundancy, and normalize features. To deal with the curse of dimensionality and smooth statistical fluctuations in high-dimensional features, we propose local reachability density (LRD). Our LRD iteratively selects a bag of engineered features with random cardinality and quantifies their average density by its k-nearest neighbors. Finally, MeetSafe constructs a Gaussian Mixture Model (GMM) with the processed features and detects AEs if it is seen as a local outlier, shown by a low density from GMM. Experimental results show that MeetSafe achieves 74%, 96%, and 79% of detection accuracy against adaptive, classic, and white-box attacks, respectively, and at least 2.3x faster than comparison methods.