相关论文: Detecting Data Contamination in Large Language Mod…

Membership inference attacks (MIAs) are widely used to assess the privacy risks associated with machine learning models. However, when these attacks are applied to pre-trained large language models (LLMs), they encounter significant…

Large Language Models (LLMs) have seen widespread adoption due to their remarkable natural language capabilities. However, when deploying them in real-world settings, it is important to align LLMs to generate texts according to acceptable…

We propose Fast-MIA (https://github.com/Nikkei/fast-mia), a Python library for efficiently evaluating membership inference attacks (MIA) against large language models (LLMs). MIA has emerged as a crucial technique for auditing privacy risks…

Machine learning (ML) models have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that ML models are vulnerable to…

Large vision-language models (LVLMs) have demonstrated outstanding performance in many downstream tasks. However, LVLMs are trained on large-scale datasets, which can pose privacy risks if training images contain sensitive information.…

Large language models (LLMs) have become essential tools for digital task assistance. Their training relies heavily on the collection of vast amounts of data, which may include copyright-protected or sensitive information. Recent studies on…

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership…

Recent advances in Large Language Models (LLMs) have enabled them to overcome their context window limitations, and demonstrate exceptional retrieval and reasoning capacities on longer context. Quesion-answering systems augmented with…

The increasing parameters and expansive dataset of large language models (LLMs) highlight the urgent demand for a technical solution to audit the underlying privacy risks and copyright issues associated with LLMs. Existing studies have…

Whether LLMs memorize their training data and what this means, from measuring privacy leakage to detecting copyright violations, has become a rapidly growing area of research. In the last few months, more than 10 new methods have been…

Language Models (LMs) typically adhere to a "pre-training and fine-tuning" paradigm, where a universal pre-trained model can be fine-tuned to cater to various specialized domains. Low-Rank Adaptation (LoRA) has gained the most widespread…

We present the first systematic Membership Inference Attack (MIA) evaluation of Large Audio Language Models (LALMs). As audio encodes non-semantic information, it induces severe train and test distribution shifts and can lead to spurious…

With the widespread application of large language models (LLM), concerns about the privacy leakage of model training data have increasingly become a focus. Membership Inference Attacks (MIAs) have emerged as a critical tool for evaluating…

Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy concerns. In this…

Large Language Models (LLMs) and Vision-Language Models (VLMs) have made significant advancements in a wide range of natural language processing and vision-language tasks. Access to large web-scale datasets has been a key factor in their…

The rapid advancement of Large Language Models (LLMs) has been driven by extensive datasets that may contain sensitive information, raising serious privacy concerns. One notable threat is the Membership Inference Attack (MIA), where…

Membership inference attacks (MIAs) aim to infer whether a data point has been used to train a machine learning model. These attacks can be employed to identify potential privacy vulnerabilities and detect unauthorized use of personal data.…

Large language models (LLMs) based recommender systems (RecSys) can adapt to different domains flexibly. It utilizes in-context learning (ICL), i.e., prompts, to customize the recommendation functions, which include sensitive historical…

Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now trained on nearly all available data, which amplifies the…

Membership inference attacks (MIA) try to detect if data samples were used to train a neural network model, e.g. to detect copyright abuses. We show that models with higher dimensional input and output are more vulnerable to MIA, and…