Quantization is a popular technique that transforms the parameter
repres...
Assessing the exploitability of software vulnerabilities at the time of
...
Recent increases in the computational demands of deep neural networks (D...
Deep learning models often raise privacy concerns as they leak informati...
Machine learning algorithms are vulnerable to data poisoning attacks. Pr...
New data processing pipelines and novel network architectures increasing...
Deep neural networks (DNNs) have been shown to tolerate "brain damage":
...
As there are increasing needs of sharing data for machine learning, ther...
While deep neural networks (DNNs) can perform complex classification tas...
Recent work has introduced attacks that extract the architecture informa...
Data poisoning is a type of adversarial attack on machine learning model...
Attacks against machine learning systems represent a growing threat as
h...
Recent measurements of the Windows code-signing certificate ecosystem ha...