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 …

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 …

Most current approaches for protecting privacy in machine learning (ML) assume that
models exist in a vacuum. Yet, in reality, these models are part of larger systems that include …

AI has undergone a remarkable evolution journey marked by groundbreaking milestones.
Like any powerful tool, it can be turned into a weapon for devastation in the wrong hands …

We study design of black-box model extraction attacks that can* send minimal number of
queries from* a* publicly available dataset* to a target ML model through a predictive API …

Malicious utilization of a query interface can compromise the confidentiality of ML-as-a-
Service (MLaaS) systems via model extraction attacks. Previous studies have proposed to …

ML models are known to be vulnerable to adversarial query attacks. In these attacks, queries
are iteratively perturbed towards a particular class without any knowledge of the target …

Ensuring the security of large language models (LLMs) is an ongoing challenge despite
their widespread popularity. Developers work to enhance LLMs security, but vulnerabilities …

Machine Learning as a Service (MLaaS) platforms have gained popularity due to their
accessibility, cost-efficiency, scalability, and rapid development capabilities. However …

Recent works developed an emerging attack, called Model Stealing (MS), to steal the
functionalities of remote models, rendering the privacy of cloud-based machine learning …