Reinforcement learning allows machines to learn from their own experienc...
Adversarial reprogramming allows stealing computational resources by
rep...
One of the most common causes of lack of continuity of online systems st...
The presence and persistence of Android malware is an on-going threat th...
Adversarial patches are optimized contiguous pixel blocks in an input im...
Although ImageNet was initially proposed as a dataset for performance
be...
Adversarial reprogramming allows repurposing a machine-learning model to...
Evaluating robustness of machine-learning models to adversarial examples...
Evaluating adversarial robustness amounts to finding the minimum perturb...
We present a novel descriptor for crowd behavior analysis and anomaly
de...
We present secml, an open-source Python library for secure and explainab...
Transferability captures the ability of an attack against a machine-lear...