Related papers: Protecting Private Code in IDE Autocomplete using …
Recent developments in deep learning have led to great success in various natural language processing (NLP) tasks. However, these applications may involve data that contain sensitive information. Therefore, how to achieve good performance…
We present the first theoretical convergence analysis of machine learning training under fully homomorphic encryption (FHE), combined with a differentially private (DP) training algorithm tailored to encrypted computation. Our approach…
An important problem in deep learning is the privacy and security of neural networks (NNs). Both aspects have long been considered separately. To date, it is still poorly understood how privacy enhancing training affects the robustness of…
Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-trained model is adapted to a wide array of tasks via fine-tuning…
Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it…
Differential privacy (DP) techniques can be applied to the federated learning model to protect data privacy against inference attacks to communication among the learning agents. The DP techniques, however, hinder achieving a greater…
Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…
Federated learning (FL) enhances privacy by keeping user data on local devices. However, emerging attacks have demonstrated that the updates shared by users during training can reveal significant information about their data. This has…
Language modeling is a keystone task in natural language processing. When training a language model on sensitive information, differential privacy (DP) allows us to quantify the degree to which our private data is protected. However,…
Protecting patient data privacy is a critical concern when deploying machine learning algorithms in healthcare. Differential privacy (DP) is a common method for preserving privacy in such settings and, in this work, we examine two key…
Machine learning (ML) models have been shown to leak private information from their training datasets. Differential Privacy (DP), typically implemented through the differential private stochastic gradient descent algorithm (DP-SGD), has…
We address the problem of learning a machine learning model from training data that originates at multiple data owners while providing formal privacy guarantees regarding the protection of each owner's data. Existing solutions based on…
CPU-based trusted execution environments (TEEs) and differential privacy (DP) have gained wide applications for private inference. Due to high inference latency in TEEs, researchers use partition-based approaches that offload linear model…
Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is…
Individual Differential Privacy (iDP) promises users control over their privacy, but this promise can be broken in practice. We reveal a previously overlooked vulnerability in sampling-based iDP mechanisms: while conforming to the iDP…
Differentially private in-context learning (DP-ICL) has recently become an active research topic due to the inherent privacy risks of in-context learning. However, existing approaches overlook a critical component of modern large language…
The superior performance of large foundation models relies on the use of massive amounts of high-quality data, which often contain sensitive, private and copyrighted material that requires formal protection. While differential privacy (DP)…
Differential privacy (DP) has become the de facto standard of privacy preservation due to its strong protection and sound mathematical foundation, which is widely adopted in different applications such as big data analysis, graph data…
Distributed multi-agent learning enables agents to cooperatively train a model without requiring to share their datasets. While this setting ensures some level of privacy, it has been shown that, even when data is not directly shared, the…
Private and public organizations regularly collect and analyze digitalized data about their associates, volunteers, clients, etc. However, because most personal data are sensitive, there is a key challenge in designing privacy-preserving…