The majority of machine learning methodologies operate with the assumption that their
environment is benign. However, this assumption does not always hold, as it is often …

Abstract Knowledge distillation is effective for producing small, high-performance neural
networks for classification, but these small networks are vulnerable to adversarial attacks …

Deep model compression has been extensively studied, and state-of-the-art methods can
now achieve high compression ratios with minimal accuracy loss. This paper studies model …

This paper proposes ElasticFlow, an elastic serverless training platform for distributed deep
learning. ElasticFlow provides a serverless interface with two distinct features:(i) users …

Great progress has been made in deep learning over the past few years, which drives the
deployment of deep learning–based applications into cyber-physical systems. But the lack of …

Deep learning has become a promising programming paradigm in software development,
owing to its surprising performance in solving many challenging tasks. Deep neural …

Machine Learning-based Intrusion Detection Systems have been proven to be very effective
in the protection of IoT Networks. However, the expansion of Adversarial Machine Learning …

Adversarial examples provoke weak reliability and potential security issues in deep neural
networks. Although adversarial training has been widely studied to improve adversarial …

This paper proposes Characteristic Examples for effectively fingerprinting deep neural
networks, featuring high-robustness to the base model against model pruning as well as low …

Deep neural networks have achieved impressive performance in many applications but their
large number of parameters lead to significant computational and storage overheads …