The advancements in machine learning (ML) opened a new opportunity to bring intelligence
to the low-end Internet-of-Things (IoT) nodes, such as microcontrollers. Conventional ML …

As machine learning becomes more widely used, the need to study its implications in
security and privacy becomes more urgent. Although the body of work in privacy has been …

Ensuring alignment, which refers to making models behave in accordance with human
intentions [1, 2], has become a critical task before deploying large language models (LLMs) …

Understanding to what extent neural networks memorize training data is an intriguing
question with practical and theoretical implications. In this paper we show that in some …

Continual Learning (CL) aims to sequentially train models on streams of incoming data that
vary in distribution by preserving previous knowledge while adapting to new data. Current …

We introduce the first model-stealing attack that extracts precise, nontrivial information from
black-box production language models like OpenAI's ChatGPT or Google's PaLM-2 …

Current model extraction attacks assume that the adversary has access to a surrogate
dataset with characteristics similar to the proprietary data used to train the victim model. This …

Abstract Machine learning models deployed as a service (MLaaS) are susceptible to model
stealing attacks, where an adversary attempts to steal the model within a restricted access …

Machine-Learning-as-a-Service (MLaaS) has become a widespread paradigm, making
even the most complex Machine Learning models available for clients via, eg, a pay-per …

This work provides the community with a timely comprehensive review of backdoor attacks
and countermeasures on deep learning. According to the attacker's capability and affected …