With the widespread application in industrial manufacturing and commercial services, well- trained deep neural networks (DNNs) are becoming increasingly valuable and crucial …
I Lederer, R Mayer, A Rauber - IEEE Transactions on Neural …, 2023 - ieeexplore.ieee.org
The commercial use of machine learning (ML) is spreading; at the same time, ML models are becoming more complex and more expensive to train, which makes intellectual property …
Z Hong, L Shen, T Liu - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Recently non-transferable learning (NTL) was proposed to restrict models' generalization toward the target domain (s) which serves as state-of-the-art solutions for intellectual …
F Suya, A Suri, T Zhang, J Hong… - … IEEE Conference on …, 2024 - ieeexplore.ieee.org
Numerous works study black-box attacks on image classifiers, where adversaries generate adversarial examples against unknown target models without having access to their internal …
Can we recover the hidden parameters of an Artificial Neural Network (ANN) by probing its input-output mapping? We propose a systematic method, calledExpand-and-Cluster'that …
Deep learning has shown incredible potential across a vast array of tasks and accompanying this growth has been an insatiable appetite for data. However, a large …
P Dissanayake, S Dutta - arXiv preprint arXiv:2405.05369, 2024 - arxiv.org
Counterfactual explanations find ways of achieving a favorable model outcome with minimum input perturbation. However, counterfactual explanations can also be exploited to …
In contrast to vast academic efforts to study AI security, few real-world reports of AI security incidents exist. Released incidents prevent a thorough investigation of the attackers' …
S Akoush, A Paleyes, A Van Looveren… - arXiv preprint arXiv …, 2022 - arxiv.org
Inference is a significant part of ML software infrastructure. Despite the variety of inference frameworks available, the field as a whole can be considered in its early days. This position …