相关论文: Mitigating Data Exfiltration Attacks through Layer…

Current Large Language Models (LLMs), even those tuned for safety and alignment, are susceptible to jailbreaking. Some have found that just further fine-tuning an aligned model with benign data (i.e., data without harmful content)…

Federated Learning (FL) is designed to prevent data leakage through collaborative model training without centralized data storage. However, it remains vulnerable to gradient reconstruction attacks that recover original training data from…

Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain…

Neural networks pose a privacy risk to training data due to their propensity to memorise and leak information. Focusing on image classification, we show that neural networks also unintentionally memorise unique features even when they occur…

Recently, serious concerns have been raised about the privacy issues related to training datasets in machine learning algorithms when including personal data. Various regulations in different countries, including the GDPR grant individuals…

Machine learning poses severe privacy concerns as it has been shown that the learned models can reveal sensitive information about their training data. Many works have investigated the effect of widely adopted data augmentation and…

Recent works have demonstrated that it is possible to reconstruct training images and their labels from gradients of an image-classification model when its architecture is known. Unfortunately, there is still an incomplete theoretical…

Federated learning (FL) is an emerging collaborative learning paradigm that aims to protect data privacy. Unfortunately, recent works show FL algorithms are vulnerable to the serious data reconstruction attacks. However, existing works lack…

Fine-tuning on open-source Large Language Models (LLMs) with proprietary data is now a standard practice for downstream developers to obtain task-specific LLMs. Surprisingly, we reveal a new and concerning risk along with the practice: the…

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…

Recent Deep Learning (DL) advancements in solving complex real-world tasks have led to its widespread adoption in practical applications. However, this opportunity comes with significant underlying risks, as many of these models rely on…

Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum. Yet, in reality, these models are part of larger systems that include components for training data filtering, output monitoring,…

Federated learning (FL) allows multiple entities to train a shared model collaboratively. Its core, privacy-preserving principle is that participants only exchange model updates, such as gradients, and never their raw, sensitive data. This…

Today's success of state of the art methods for semantic segmentation is driven by large datasets. Data is considered an important asset that needs to be protected, as the collection and annotation of such datasets comes at significant…

This paper surveys the landscape of security and data attacks on machine unlearning, with a focus on financial and e-commerce applications. We discuss key privacy threats such as Membership Inference Attacks and Data Reconstruction Attacks,…

Privacy data protection in the medical field poses challenges to data sharing, limiting the ability to integrate data across hospitals for training high-precision auxiliary diagnostic models. Traditional centralized training methods are…

Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis. These applications are trained on datasets from many FL…

Deep Neural Network (DNN) models have been shown to have high empirical privacy leakages. Clinical language models (CLMs) trained on clinical data have been used to improve performance in biomedical natural language processing tasks. In…

Neural language models (LMs) are vulnerable to training data extraction attacks due to data memorization. This paper introduces a novel attack scenario wherein an attacker adversarially fine-tunes pre-trained LMs to amplify the exposure of…

Federated Learning (FL) is a distributed learning paradigm that enhances users privacy by eliminating the need for clients to share raw, private data with the server. Despite the success, recent studies expose the vulnerability of FL to…