Current anti-spoofing and audio deepfake detection systems use either
ma...
For real-world applications of machine learning (ML), it is essential th...
Model inversion (MI) attacks allow to reconstruct average per-class
repr...
Machine learning is a data-driven discipline, and learning success is la...
Neural networks follow a gradient-based learning scheme, adapting their
...
Current text-to-speech algorithms produce realistic fakes of human voice...
Automatic speech recognition (ASR) is improving ever more at mimicking h...
Automatic speech recognition (ASR) systems are ubiquitously present in o...
The recent emergence of deepfakes, computerized realistic multimedia fak...
We present our analysis of a significant data artifact in the official
2...
An important problem in deep learning is the privacy and security of neu...
Data poisoning is one of the most relevant security threats against mach...
Many defensive measures in cyber security are still dominated by heurist...
Two widely used techniques for training supervised machine learning mode...
Adversarial examples tremendously threaten the availability and integrit...
Adversarial data poisoning is an effective attack against machine learni...
Neural Networks (NNs) are vulnerable to adversarial examples. Such input...
Inspired by the recent advances in coverage-guided analysis of neural
ne...
In recent years Deep Neural Networks (DNNs) have achieved remarkable res...
Software testing is becoming a critical part of the development cycle of...
Fuzzing is the process of finding security vulnerabilities in
input-proc...