Maura Pintor

Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes

2021 · Open Repository and Bibliography (University of Liège)

Although ImageNet was initially proposed as a dataset for performance benchmarking in the domain of computer vision, it also enabled a variety of other research efforts. Adversarial machine learning is one such research effort, employing …

Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks

2023

Neural network pruning has shown to be an effective technique for reducing the network size, trading desirable properties like generalization and robustness to adversarial attacks for higher sparsity. Recent work has claimed that adversarial pruning …

Silent Until Sparse: Backdoor Attacks on Semi-Structured Sparsity

2025 · arXiv (Cornell University)

Semi-structured (2:4) sparsity is a widely adopted pruning method in modern hardware and software ecosystems (e.g., NVIDIA Sparse Tensor Cores and PyTorch), achieving up to 2X faster inference and reduced memory footprint with negligible accuracy …