相关论文: Training Data Attribution (TDA): Examining Its Ado…

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…

Exploring the socio-technical challenges confronting the adoption of AI in organisational settings is something that has so far been largely absent from the related literature. In particular, research into requirements for trustworthy AI…

The goal of data attribution is to trace the model's predictions through the learning algorithm and back to its training data. thereby identifying the most influential training samples and understanding how the model's behavior leads to…

While artificial intelligence has the potential to process vast amounts of data, generate new insights, and unlock greater productivity, its widespread adoption may entail unforeseen consequences. We identify conditions under which AI, by…

All famous machine learning algorithms that comprise both supervised and semi-supervised learning work well only under a common assumption: the training and test data follow the same distribution. When the distribution changes, most…

Motivated by the advancing computational capacity of distributed end-user equipments (UEs), as well as the increasing concerns about sharing private data, there has been considerable recent interest in machine learning (ML) and artificial…

Transfer learning is widely used for transferring knowledge from a source domain to the target domain where the labeled data is scarce. Recently, deep transfer learning has achieved remarkable progress in various applications. However, the…

As the use of Generative Artificial Intelligence tools have grown in higher education and research, there have been increasing calls for transparency and granularity around the use and attribution of the use of these tools. Thus far, this…

Knowing more about the data used to build AI systems is critical for allowing different stakeholders to play their part in ensuring responsible and appropriate deployment and use. Meanwhile, a 2023 report shows that data transparency lags…

Convergence bounds are one of the main tools to obtain information on the performance of a distributed machine learning task, before running the task itself. In this work, we perform a set of experiments to assess to which extent, and in…

A number of recent works have demonstrated that API access to machine learning models leaks information about the dataset records used to train the models. Further, the work of \cite{somesh-overfit} shows that such membership inference…

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

Tool-augmented large language models (LLMs) are often trained on datasets of query-response pairs, which embed the ability to use tools or APIs directly into the parametric knowledge of LLMs. Tool-augmented LLMs need the ability to forget…

Ensuring fairness in AI systems is critical, especially in high-stakes domains such as lending, hiring, and healthcare. This urgency is reflected in emerging global regulations that mandate fairness assessments and independent bias audits.…

Test-time adaptation (TTA) addresses distribution shifts for streaming test data in unsupervised settings. Currently, most TTA methods can only deal with minor shifts and rely heavily on heuristic and empirical studies. To advance TTA under…

While Mechanistic Interpretability has identified interpretable circuits in LLMs, their causal origins in training data remain elusive. We introduce Mechanistic Data Attribution (MDA), a scalable framework that employs Influence Functions…

Artificial intelligence (AI) has transformed various sectors and institutions, including education and healthcare. Although AI offers immense potential for innovation and problem solving, its integration also raises significant ethical…

Artificial intelligence (AI) is increasingly intervening in our lives, raising widespread concern about its unintended and undeclared side effects. These developments have brought attention to the problem of AI auditing: the systematic…

Algorithmic fairness and privacy are essential pillars of trustworthy machine learning. Fair machine learning aims at minimizing discrimination against protected groups by, for example, imposing a constraint on models to equalize their…

Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms…