4 papers
Robust Auto-associative Memory via Convolutional Restricted Hopfield Networks
Ci Lin, Tet Yeap, Iluju Kiringa
Associative memory models play a fundamental role in pattern retrieval, but their performance often degrades under adversarial perturbations and severe input corruptions. Existing…
Preserving Temporal Dynamics in Time Series Generation
Ci Lin, Futong Li, Tet Yeap +1
Time-series data augmentation plays a crucial role in regression-oriented forecasting tasks, where limited data restricts the performance of deep learning models. While Generative…
Robust Bidirectional Associative Memory via Regularization Inspired by the Subspace Rotation Algorithm
Ci Lin, Tet Yeap, Iluju Kiringa +1
Bidirectional Associative Memory (BAM) trained with Bidirectional Backpropagation (B-BP) often suffers from poor robustness and high sensitivity to noise and adversarial attacks. T…
DeepDefense: Robust Learning via Layer-Wise Gradient-Feature Alignment
Ci Lin, Tet Yeap, Iluju Kiringa +1
Deep neural networks are known to be vulnerable to adversarial perturbations, which are small, carefully crafted inputs that lead to incorrect predictions. In this paper, we propos…