Related papers: Towards Robust and Privacy-preserving Text Represe…
Public pretraining is a promising approach to improve differentially private model training. However, recent work has noted that many positive research results studying this paradigm only consider in-distribution tasks, and may not apply to…
Many current Internet services rely on inferences from models trained on user data. Commonly, both the training and inference tasks are carried out using cloud resources fed by personal data collected at scale from users. Holding and using…
Authors writing documents imprint identifying information within their texts: vocabulary, registry, punctuation, misspellings, or even emoji usage. Previous works use hand-crafted features or classification tasks to train their authorship…
The study of Differential Privacy (DP) in Natural Language Processing often views the task of text privatization as a $\textit{rewriting}$ task, in which sensitive input texts are rewritten to hide explicit or implicit private information.…
Hierarchical text classification consists in classifying text documents into a hierarchy of classes and sub-classes. Although artificial neural networks have proved useful to perform this task, unfortunately they can leak training data…
Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used to solve several privacy concerns (Dwork et al., 2014).…
We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…
Recent privacy research on large language models (LLMs) has shown that they achieve near-human-level performance at inferring personal data from online texts. With ever-increasing model capabilities, existing text anonymization methods are…
Real-world data is usually segmented by attributes and distributed across different parties. Federated learning empowers collaborative training without exposing local data or models. As we demonstrate through designed attacks, even with a…
This paper addresses the ethical concerns arising from the use of unauthorized public data in deep learning models and proposes a novel solution. Specifically, building on the work of Huang et al. (2021), we extend their bi-level…
User-driven privacy allows individuals to control whether and at what granularity their data is shared, leading to datasets that mix original, generalized, and missing values within the same records and attributes. While such…
The task of obfuscating writing style using sequence models has previously been investigated under the framework of obfuscation-by-transfer, where the input text is explicitly rewritten in another style. These approaches also often lead to…
Large language models (LLMs) show early signs of artificial general intelligence but struggle with hallucinations. One promising solution to mitigate these hallucinations is to store external knowledge as embeddings, aiding LLMs in…
The remarkable success of machine learning has fostered a growing number of cloud-based intelligent services for mobile users. Such a service requires a user to send data, e.g. image, voice and video, to the provider, which presents a…
Text embeddings are fundamental to many natural language processing (NLP) tasks, extensively applied in domains such as recommendation systems and information retrieval (IR). Traditionally, transmitting embeddings instead of raw text has…
Transfer learning is an effective technique to improve a target recommender system with the knowledge from a source domain. Existing research focuses on the recommendation performance of the target domain while ignores the privacy leakage…
Anonymizing sensitive information in user text is essential for privacy, yet existing methods often apply uniform treatment across attributes, which can conflict with communicative intent and obscure necessary information. This is…
Accurately learning from user data while ensuring quantifiable privacy guarantees provides an opportunity to build better Machine Learning (ML) models while maintaining user trust. Recent literature has demonstrated the applicability of a…
Ensuring privacy during inference stage is crucial to prevent malicious third parties from reconstructing users' private inputs from outputs of public models. Despite a large body of literature on privacy preserving learning (which ensures…
Learning with graphs has attracted significant attention recently. Existing representation learning methods on graphs have achieved state-of-the-art performance on various graph-related tasks such as node classification, link prediction,…