Artificial neural networks are prone to being fooled by carefully perturbed inputs which cause an egregious misclassification. These textit{adversarial} attacks...
Shortcut learning, or `Clever Hans effect` refers to situations where a learning agent (e.g., deep neural networks) learns spurious correlations...
In many VoIP systems, Voice Activity Detection (VAD) is often used on VoIP traffic to suppress packets of silence in...
In many VoIP systems, Voice Activity Detection (VAD) is often used on VoIP traffic to suppress packets of silence in...
In Federated Learning (FL) and many other distributed training frameworks, collaborators can hold their private data locally and only share...
Canary exposure, introduced in Carlini et al. is frequently used to empirically evaluate, or audit, the privacy of machine learning...
In Federated Learning (FL) and many other distributed training frameworks, collaborators can hold their private data locally and only share...
The rapid digitalisation of SMEs, further expedited as a business continuity measure against Covid19 impact, has brought along major cybersecurity...
Canary exposure, introduced in Carlini et al. is frequently used to empirically evaluate, or audit, the privacy of machine learning...
The smart-grid introduces several new data-gathering, communication, and information-sharing capabilities into the electrical system, as well as additional privacy threats,...
