Aug 2026· International Symposium on Low Power Electronics and Design· pp. 1-7· 0 citations· 22 references
Computer Science
TL;DR
Across CIFAR10, COIL100, and ETH80 under FGSM and Genetic Attack, ViT + Classical HDC degrades more gracefully than Pure HDC and ViT + HDC baselines, and achieves higher normalized AURC, lower attack-time decision margins, and larger gains from partial adversarial retraining.
Abstract
Neuro-symbolic models may improve robustness by combining learned representations with structured composition, but their behavior under adversarial perturbation remains underexplored. We study a hybrid pipeline that fuses ViT features with classical descriptors through Hyperdimensional Computing (HDC). Across CIFAR10 (Subset), COIL100, and ETH80 under FGSM and Genetic Attack, ViT + Classical HDC degrades more gracefully than Pure HDC and ViT + HDC baselines. It achieves higher normalized AURC, lower attack-time decision margins, and larger gains from partial adversarial retraining. These results suggest that classical-neural fusion within HDC is a promising direction for robustness under the evaluated threat models.
VisionDES is introduced, a novel DES framework for image classification that uses deep model embeddings to estimate classifier competence and consistently outperforms static ensembles and existing uncertainty-based DES methods, improving robust accuracy under strong attacks and under distribution shifts.
Firuz Juraev, Mohammad Abuhamad, Shaker El-Sappagh et al.· Proceedings of the 32nd ACM...· 0 citations
Machine learning models remain highly susceptible to adversarial perturbations, which can cause them to produce incorrect predictions while remaining imperceptible to humans. Existing defense methods usually emphasize either detection or robust training in isolation, which limits their capability to deal with adaptive...
B. Durga, Adike Sri Vathsankitha, Aechikuchi Sathwika et al.· 2026 International Conferenc...· 0 citations
Distributional Adversarial Recurrent Training (DART), a training framework that replaces single-point supervision with a local target distribution around the ground-truth solution and aligns model outputs with this distribution through an adversarial objective, is proposed.
This work introduces Oscillatory Predictive Learning (OPL), a two-stage framework that combines Artificial Kuramoto Oscillatory Neurons (AKOrN) with predictive self-supervised pretraining using X-PhiNet and compares it with other randomized adversarial defense methods that provide precise, reproducible, and strong atta...
M. Habibi, Klea Ziu, Martin Takác et al.· 0 citations
This work establishes a high-probability generalization bound for ViTs in classification tasks under adversarial settings, and elucidates the roles of several factors in mitigating perturbation effects, norm regularization of weight matrices and depth-wise propagation constraints on layer-wise norms.
Zi-Wen Jiang, Chang Cao, Han Li et al.· Proceedings of the Thirty-Fi...· 0 citations
An adversarial training algorithm is developed and shown to be effectiveness in increasing robustness against adversarial missingness on three MuJoCo benchmark environments and achieves better robustness on all three tasks.
Paul Stahlhofen, Luca Hermes, Tim Kochs et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
