相关论文: Don't Push the Button! Exploring Data Leakage Risk…

Classifiers and other statistics-based machine learning (ML) techniques generalize, or learn, based on various statistical properties of the training data. The assumption underlying statistical ML resulting in theoretical or empirical…

Machine learning (ML) is poised to drive innovations in clinical microbiomics, such as in disease diagnostics and prognostics. However, the successful implementation of ML in these domains necessitates the development of reproducible,…

Large Language Models for Code (LLMs4Code) have achieved strong performance in code generation, but recent studies reveal that they may memorize and leak sensitive information contained in training data, posing serious privacy risks. To…

Fairness in machine learning (ML) has garnered significant attention in recent years. While existing research has predominantly focused on the distributive fairness of ML models, there has been limited exploration of procedural fairness.…

Research is facing a reproducibility crisis, in which the results and findings of many studies are difficult or even impossible to reproduce. This is also the case in machine learning (ML) and artificial intelligence (AI) research. Often,…

Data used to train supervised machine learning models are commonly split into independent training, validation, and test sets. This paper illustrates that complex data leakage cases have occurred in the no-reference image and video quality…

Cascading failures pose a significant threat to power grids and have garnered considerable research interest in the power system domain. The inherent uncertainty and severe impact associated with cascading failures have raised concerns,…

Privacy and security challenges in Machine Learning (ML) have become increasingly severe, along with ML's pervasive development and the recent demonstration of large attack surfaces. As a mature system-oriented approach, Confidential…

With the extensive use of machine learning technologies, data providers encounter increasing privacy risks. Recent legislation, such as GDPR, obligates organizations to remove requested data and its influence from a trained model. Machine…

Transfer learning is a useful machine learning framework that allows one to build task-specific models (student models) without significantly incurring training costs using a single powerful model (teacher model) pre-trained with a large…

Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged…

Protecting users' privacy over the Internet is of great importance; however, it becomes harder and harder to maintain due to the increasing complexity of network protocols and components. Therefore, investigating and understanding how data…

To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that a differential analysis of language model snapshots before and after an update…

Detection of easily missed hidden patterns with fast processing power makes machine learning (ML) indispensable to today's healthcare system. Though many ML applications have already been discovered and many are still under investigation,…

Recently, advances in deep learning have been observed in various fields, including computer vision, natural language processing, and cybersecurity. Machine learning (ML) has demonstrated its ability as a potential tool for anomaly…

Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are…

Recently software development companies started to embrace Machine Learning (ML) techniques for introducing a series of advanced functionality in their products such as personalisation of the user experience, improved search, content…

Pointwise maximal leakage (PML) is an operationally meaningful privacy measure that quantifies the amount of information leaking about a secret $X$ to a single outcome of a related random variable $Y$. In this paper, we extend the notion of…

A major concern of Machine Learning (ML) models is their opacity. They are deployed in an increasing number of applications where they often operate as black boxes that do not provide explanations for their predictions. Among others, the…

Safeguarding the Intellectual Property (IP) of data has become critically important as machine learning applications continue to proliferate, and their success heavily relies on the quality of training data. While various mechanisms exist…