CHIP: Chameleon Hash-Based Irreversible Passport for Robust Deep Model Ownership Verification and Active Usage Control

The pervasion of large-scale Deep Neural Networks DNNs and their enormous training costs make their intellectual property IP protection of paramount importance. Recently introduced passport-based methods attempt to steer DNN watermarking towards strengthening ownership verification against...

RADEP: a Resilient Adaptive Defense Framework against Model Extraction Attacks

Machine Learning as a Service MLaaS enables users to leverage powerful machine learning models through cloud-based APIs, offering scalability and ease of deployment. However, these services are vulnerable to model extraction attacks, where adversaries repeatedly query the application programming...

Private Transformer Inference in MLaaS: a Survey

Transformer models have revolutionized AI, powering applications like content generation and sentiment analysis. However, their deployment in Machine Learning as a Service MLaaS raises significant privacy concerns, primarily due to the centralized processing of sensitive user data. Private...

On the Interplay of Explainability, Privacy and Predictive Performance with Explanation-Assisted Model Extraction

Machine Learning as a Service MLaaS has gained important attraction as a means for deploying powerful predictive models, offering ease of use that enables organizations to leverage advanced analytics without substantial investments in specialized infrastructure or expertise. However, MLaaS...

Vulnerabilities fixed in Microsoft Azure

Microsoft has fixed vulnerabilities in several Azure components. A malicious party could exploit the vulnerabilities to grant themselves elevated privileges, gain access to sensitive data, or to impersonate another user via a cross-site scripting attack. Such an attack can lead to execution of...

Microsoft Azure Machine Learning Service JWT Cleartext Storage of Credentials Information Disclosure Vulnerability

This vulnerability allows remote attackers to disclose sensitive information on Microsoft Azure. Authentication is required to exploit this vulnerability. The specific flaw exists within the handling of JWT tokens within Azure Machine Learning Service workbooks. The issue results from storing...