相关论文: Unintended Memorization and Timing Attacks in Name…

The automated and timely conversion of cybersecurity information from unstructured online sources, such as blogs and articles to more formal representations has become a necessity for many applications in the domain nowadays. Named Entity…

Machine learning algorithms, when applied to sensitive data, pose a distinct threat to privacy. A growing body of prior work demonstrates that models produced by these algorithms may leak specific private information in the training data to…

Past work has shown that large language models are susceptible to privacy attacks, where adversaries generate sequences from a trained model and detect which sequences are memorized from the training set. In this work, we show that the…

Frontier AI systems are making transformative impacts across society, but such benefits are not without costs: models trained on web-scale datasets containing personal and private data raise profound concerns about data privacy and…

Named entity recognition (NER) is frequently addressed as a sequence classification task where each input consists of one sentence of text. It is nevertheless clear that useful information for the task can often be found outside of the…

Membership inference (MI) determines if a sample was part of a victim model training set. Recent development of MI attacks focus on record-level membership inference which limits their application in many real-world scenarios. For example,…

Membership Inference Attacks (MIAs) pose a significant privacy risk by enabling adversaries to determine if a specific data point was part of a model's training set. This work empirically investigates whether MU algorithms can function as a…

Language models (LMs) risk inadvertently memorizing and divulging sensitive or personally identifiable information (PII) seen in training data, causing privacy concerns. Current approaches to address this issue involve costly dataset…

In this paper we propose a new membership attack method called co-membership attacks against deep generative models including Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs). Specifically, membership attack aims…

Training data memorization in language models impacts model capability (generalization) and safety (privacy risk). This paper focuses on analyzing prompts' impact on detecting the memorization of 6 masked language model-based named entity…

Privacy attacks on machine learning models aim to identify the data that is used to train such models. Such attacks, traditionally, are studied on static models that are trained once and are accessible by the adversary. Motivated to meet…

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

Named Entity Recognition (NER) is a key step in the creation of structured data from digitised historical documents. Traditional NER approaches deal with flat named entities, whereas entities often are nested. For example, a postal address…

Recent progress in language model pre-training has led to important improvements in Named Entity Recognition (NER). Nonetheless, this progress has been mainly tested in well-formatted documents such as news, Wikipedia, or scientific…

Recent years have witnessed the tremendous success of diffusion models in data synthesis. However, when diffusion models are applied to sensitive data, they also give rise to severe privacy concerns. In this paper, we systematically present…

Named entity recognition (NER) is an extensively studied task that extracts and classifies named entities in a text. NER is crucial not only in downstream language processing applications such as relation extraction and question answering…

Large language models have gained significant popularity because of their ability to generate human-like text and potential applications in various fields, such as Software Engineering. Large language models for code are commonly trained on…

Large language models (LLMs) are increasingly trained on tabular data, which, unlike unstructured text, often contains personally identifiable information (PII) in a highly structured and explicit format. As a result, privacy risks arise,…

In a sentence, certain words are critical for its semantic. Among them, named entities (NEs) are notoriously challenging for neural models. Despite their importance, their accurate handling has been neglected in speech-to-text (S2T)…

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…