The prosperity of machine learning has been accompanied by increasing attacks on the
training process. Among them, poisoning attacks have become an emerging threat during …

The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many
socio-economic and environmental challenges; however, this cannot happen without …

While recent works have indicated that federated learning (FL) may be vulnerable to
poisoning attacks by compromised clients, their real impact on production FL systems is not …

Recent studies have shown that DNNs can be compromised by backdoor attacks crafted at
training time. A backdoor attack installs a backdoor into the victim model by injecting a …

With the success of deep learning algorithms in various domains, studying adversarial
attacks to secure deep models in real world applications has become an important research …

Recently, NLP has seen a surge in the usage of large pre-trained models. Users download
weights of models pre-trained on large datasets, then fine-tune the weights on a task of their …

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks.
Specifically, by injecting a small number of maliciously constructed inputs into the training …

As machine learning becomes widely used for automated decisions, attackers have strong
incentives to manipulate the results and models generated by machine learning algorithms …

Abstract Machine learning systems trained on user-provided data are susceptible to data
poisoning attacks, whereby malicious users inject false training data with the aim of …

Transferability captures the ability of an attack against a machine-learning model to be
effective against a different, potentially unknown, model. Empirical evidence for …