Related papers: De-Anonymization at Scale via Tournament-Style Att…

The recent surge in high-quality open-source Generative AI text models (colloquially: LLMs), as well as efficient finetuning techniques, have opened the possibility of creating high-quality personalized models that generate text attuned to…

Unstructured text from legal, medical, and administrative sources offers a rich but underutilized resource for research in public health and the social sciences. However, large-scale analysis is hampered by two key challenges: the presence…

Maintaining anonymity in natural language communication remains a challenging task. Even when the number of candidate authors is large, standard authorship attribution techniques that analyze writing style predict the original author with…

Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely…

Fine-tuning large language models (LLMs) on custom datasets has become a standard approach for adapting these models to specific domains and applications. However, recent studies have shown that such fine-tuning can lead to significant…

While semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either all unlabeled examples or the unlabeled examples with a…

Fine-tuning large language models (LLMs) using diverse datasets is crucial for enhancing their overall performance across various domains. In practical scenarios, existing methods based on modeling the mixture proportions of data…

The problem of unveiling the author of a given text document from multiple candidate authors is called authorship attribution. Manifold word-based stylistic markers have been successfully used in deep learning methods to deal with the…

Recently, powerful Large Language Models (LLMs) have become easily accessible to hundreds of millions of users world-wide. However, their strong capabilities and vast world knowledge do not come without associated privacy risks. In this…

Probabilistic reasoning is a key aspect of both human and artificial intelligence that allows for handling uncertainty and ambiguity in decision-making. In this paper, we introduce a new numerical reasoning task under uncertainty for large…

Present Large Language Models (LLM) self-training methods always under-sample on challenging queries, leading to inadequate learning on difficult problems which limits LLMs' ability. Therefore, this work proposes a difficulty-aware…

Components of machine learning systems are not (yet) perceived as security hotspots. Secure coding practices, such as ensuring that no execution paths depend on confidential inputs, have not yet been adopted by ML developers. We initiate…

Large Language Models (LLMs) are trained on massive web-crawled corpora. This poses risks of leakage, including personal information, copyrighted texts, and benchmark datasets. Such leakage leads to undermining human trust in AI due to…

The scarcity of high-quality annotated medical data, particularly in mental health, poses a significant bottleneck for training robust machine learning models. Privacy regulations restrict data sharing, making synthetic data generation a…

Language is far more than a communication tool. A wealth of information - including but not limited to the identities, psychological states, and social contexts of its users - can be gleaned through linguistic markers, and such insights are…

Data generalization is a powerful technique for sanitizing multi-attribute data for publication. In a multidimensional model, a subset of attributes called the quasi-identifiers (QI) are used to define the space and a generalization scheme…

Over the last decade, proliferation of various online platforms and their increasing adoption by billions of users have heightened the privacy risk of a user enormously. In fact, security researchers have shown that sparse microdata…

Users interacting with large language models (LLMs) under their real identifiers often unknowingly risk disclosing private information. Automatically notifying users whether their queries leak privacy and which phrases leak what private…

While de-identification models can help conceal the identity of the individuals mentioned in a document, they fail to address linkage risks, defined as the potential to map the de-identified text back to its source. One straightforward way…

The increasing prevalence of AI-generated content alongside human-written text underscores the need for reliable discrimination methods. To address this challenge, we propose a novel framework with textual embeddings from Pre-trained…