相关论文: Membership Inference on Word Embedding and Beyond

Machine learning (ML) models are known to be vulnerable to a number of attacks that target the integrity of their predictions or the privacy of their training data. To carry out these attacks, a black-box adversary must typically possess…

Inference attacks against Machine Learning (ML) models allow adversaries to learn sensitive information about training data, model parameters, etc. While researchers have studied, in depth, several kinds of attacks, they have done so in…

Membership Inference Attacks exploit the vulnerabilities of exposing models trained on customer data to queries by an adversary. In a recently proposed implementation of an auditing tool for measuring privacy leakage from sensitive…

Membership inference attacks (MIAs) against machine learning (ML) models aim to determine whether a given data point was part of the model training data. These attacks may pose significant privacy risks to individuals whose sensitive data…

Member inference (MI) attacks aim to determine if a specific data sample was used to train a machine learning model. Thus, MI is a major privacy threat to models trained on private sensitive data, such as medical records. In MI attacks one…

Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications rely on having a good semantic representation of text into…

Embedding matrices are key components in neural natural language processing (NLP) models that are responsible to provide numerical representations of input tokens.\footnote{In this paper words and subwords are referred to as \textit{tokens}…

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…

Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data. However, it is unclear if simpler generative models, like topic models, share similar vulnerabilities. In this…

In a membership inference attack, an attacker aims to infer whether a data sample is in a target classifier's training dataset or not. Specifically, given a black-box access to the target classifier, the attacker trains a binary classifier,…

With the rapid advancement of diffusion-based image-generative models, the quality of generated images has become increasingly photorealistic. Moreover, with the release of high-quality pre-trained image-generative models, a growing number…

Text anomaly detection is a critical task in natural language processing (NLP), with applications spanning fraud detection, misinformation identification, spam detection and content moderation, etc. Despite significant advances in large…

Large language models (LLMs) are trained on massive corpora that may contain sensitive information, creating privacy risks under membership inference attacks (MIAs). Knowledge distillation is widely used to compress LLMs into smaller…

Transfer learning is a useful machine learning framework that allows one to build task-specific models (student models) without significantly incurring training costs using a single powerful model (teacher model) pre-trained with a large…

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…

Large language models (LLMs) acquire knowledge across diverse domains such as science, history, and geography encountered during generative pre-training. However, due to their stochasticity, it is difficult to predict what LLMs have…

Learning word embeddings has received a significant amount of attention recently. Often, word embeddings are learned in an unsupervised manner from a large collection of text. The genre of the text typically plays an important role in the…

Recently, adapting the idea of self-supervised learning (SSL) on continuous speech has started gaining attention. SSL models pre-trained on a huge amount of unlabeled audio can generate general-purpose representations that benefit a wide…

Word embeddings are an essential instrument in many NLP tasks. Most available resources are trained on general language from Web corpora or Wikipedia dumps. However, word embeddings for domain-specific language are rare, in particular for…

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…