The success of machine learning is fueled by the increasing availability of computing power
and large training datasets. The training data is used to learn new models or update existing …

Sponge examples are test-time inputs optimized to increase energy consumption and
prediction latency of deep networks deployed on hardware accelerators. By increasing the …

In this paper, we improve the robustness of Machine Learning (ML) classifiers against
training-time attacks by linking the risk of training data being tampered with to the …

Deep learning models undergo a significant increase in the number of parameters they
possess, leading to the execution of a larger number of operations during inference. This …

Backdoor attacks inject poisoning samples during training, with the goal of forcing a
machine learning model to output an attacker-chosen class when presented with a specific …

We study indiscriminate poisoning for linear learners where an adversary injects a few
crafted examples into the training data with the goal of forcing the induced model to incur …

Nowadays, Machine Learning (ML) solutions are widely adopted in modern malware and
network intrusion detection systems. While these algorithms offer great performance, several …

RGB-D object recognition systems improve their predictive performances by fusing color and
depth information, outperforming neural network architectures that rely solely on colors …

Can a poisoned machine learning (ML) model passively recover from its adversarial
manipulation by retraining with new samples, and regain non-poisoned performance? And if …

The perturbation analysis of linear solvers applied to systems arising broadly in machine
learning settings--for instance, when using linear regression models--establishes an …