Related papers: Quantifying the Privacy Risks of Learning High-Dim…
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…
Machine learning models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other methods, substitute model training is an all-encompassing attack applicable to any machine learning…
Tabular data plays an important role in many fields and industries, including those with elevated privacy considerations and risks. As such, there is a rising interest in generating high-quality synthetic proxies for real tabular data as a…
Despite machine learning models being widely used today, the relationship between a model and its training dataset is not well understood. We explore correlation inference attacks, whether and when a model leaks information about the…
Distribution inference, sometimes called property inference, infers statistical properties about a training set from access to a model trained on that data. Distribution inference attacks can pose serious risks when models are trained on…
Data lakes enable the training of powerful machine learning models on sensitive, high-value medical datasets, but also introduce serious privacy risks due to potential leakage of protected health information. Recent studies show adversaries…
Deep learning has gained tremendous success and great popularity in the past few years. However, deep learning systems are suffering several inherent weaknesses, which can threaten the security of learning models. Deep learning's wide use…
Within the machine learning community, reconstruction attacks are a principal attack of concern and have been identified even in federated learning, which was designed with privacy preservation in mind. In federated learning, it has been…
Large Language Models (LLMs) have shown greatly enhanced performance in recent years, attributed to increased size and extensive training data. This advancement has led to widespread interest and adoption across industries and the public.…
To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that…
The wide adoption and application of Masked language models~(MLMs) on sensitive data (from legal to medical) necessitates a thorough quantitative investigation into their privacy vulnerabilities -- to what extent do MLMs leak information…
Thanks to the explosive growth of data and the development of computational resources, it is possible to build pre-trained models that can achieve outstanding performance on various tasks, such as neural language processing, computer…
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…
Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are…
Diffusion models have recently gained significant attention in both academia and industry due to their impressive generative performance in terms of both sampling quality and distribution coverage. Accordingly, proposals are made for…
Bayesian deep learning is recently regarded as an intrinsic way to characterize the weight uncertainty of deep neural networks~(DNNs). Stochastic Gradient Langevin Dynamics~(SGLD) is an effective method to enable Bayesian deep learning on…
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…
Recent attacks on Machine Learning (ML) models such as evasion attacks with adversarial examples and models stealing through extraction attacks pose several security and privacy threats. Prior work proposes to use adversarial training to…
This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…
Adversarial training was introduced as a way to improve the robustness of deep learning models to adversarial attacks. This training method improves robustness against adversarial attacks, but increases the models vulnerability to privacy…