相关论文: Exploring the limits of strong membership inferenc…

Large language models (LLMs) can leak sensitive training data through memorization and membership inference attacks. Prior work has primarily focused on strong adversarial assumptions, including attacker access to entire samples or long,…

The rapid scaling of large language models (LLMs) has raised concerns about the transparency and fair use of the data used in their pretraining. Detecting such content is challenging due to the scale of the data and limited exposure of each…

As the capabilities of pre-trained large language models (LLMs) continue to advance, the "pre-train and fine-tune" paradigm has become increasingly mainstream, leading to the development of various fine-tuning methods. However, the privacy…

Large language models (LLMs) are trained on massive web-scale corpora, raising growing concerns about privacy and copyright. Membership inference attacks (MIAs) aim to determine whether a given example was used during training. Existing LLM…

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…

The data used to train deep neural network (DNN) models in applications such as healthcare and finance typically contain sensitive information. A DNN model may suffer from overfitting. Overfitted models have been shown to be susceptible to…

Most membership inference attacks (MIAs) against Large Language Models (LLMs) rely on global signals, like average loss, to identify training data. This approach, however, dilutes the subtle, localized signals of memorization, reducing…

Retrieval-augmented generation (RAG) mitigates the hallucination problem in large language models (LLMs) and has proven effective for personalized usages. However, delivering private retrieved documents directly to LLMs introduces…

Machine learning models can leak private information about their training data. The standard methods to measure this privacy risk, based on membership inference attacks (MIAs), only check if a given data point \textit{exactly} matches a…

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…

Detecting LLM training data is generally framed as a membership inference attack (MIA) problem. However, conventional MIAs operate passively on fixed model weights, using log-likelihoods or text generations. In this work, we introduce…

As a long-term threat to the privacy of training data, membership inference attacks (MIAs) emerge ubiquitously in machine learning models. Existing works evidence strong connection between the distinguishability of the training and testing…

With the emergence of new evaluation metrics and attack methodologies for Membership Inference Attacks (MIA), it becomes essential to reevaluate previously accepted assumptions. In this paper, we revisit the longstanding debate regarding…

A Membership Inference Attack (MIA) assesses how much a trained machine learning model reveals about its training data by determining whether specific query instances were included in the dataset. We classify existing MIAs into adaptive or…

Federated Large Language Models (FedLLMs) enable multiple parties to collaboratively fine-tune LLMs without sharing raw data, addressing challenges of limited resources and privacy concerns. Despite data localization, shared gradients can…

Previous studies have developed fairness methods for biased models that exhibit discriminatory behaviors towards specific subgroups. While these models have shown promise in achieving fair predictions, recent research has identified their…

Training machine learning models on privacy-sensitive data has become a popular practice, driving innovation in ever-expanding fields. This has opened the door to new attacks that can have serious privacy implications. One such attack, the…

Since machine learning model is often trained on a limited data set, the model is trained multiple times on the same data sample, which causes the model to memorize most of the training set data. Membership Inference Attacks (MIAs) exploit…

Recommender systems (RecSys) have been widely applied to various applications, including E-commerce, finance, healthcare, social media and have become increasingly influential in shaping user behavior and decision-making, highlighting their…

The potential of transformer-based LLMs risks being hindered by privacy concerns due to their reliance on extensive datasets, possibly including sensitive information. Regulatory measures like GDPR and CCPA call for using robust auditing…