Related papers: When Tables Leak: Attacking String Memorization in…
This paper extends the Classification Error Gauge (x-CEG) framework, originally developed for measuring the privacy-utility trade-off in tabular datasets, to privacy auditing of Large Language Models (LLMs). We propose LLM-CEG, a systematic…
Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we consider a…
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 pervasive deployment of deep learning models across critical domains has concurrently intensified privacy concerns due to their inherent propensity for data memorization. While Membership Inference Attacks (MIAs) serve as the gold…
Graph Neural Networks (GNNs), specifically designed to process the graph data, have achieved remarkable success in various applications. Link stealing attacks on graph data pose a significant privacy threat, as attackers aim to extract…
The generative Artificial Intelligence (AI) tools based on Large Language Models (LLMs) use billions of parameters to extensively analyse large datasets and extract critical private information such as, context, specific details,…
Synthetic data is emerging as one of the most promising solutions to share individual-level data while safeguarding privacy. While membership inference attacks (MIAs), based on shadow modeling, have become the standard to evaluate the…
Membership Inference Attacks (MIAs) pose a critical privacy threat by enabling adversaries to determine whether a specific sample was included in a model's training dataset. Despite extensive research on MIAs, systematic comparisons between…
The rise of generative image models leads to privacy concerns when it comes to the huge datasets used to train such models. This paper investigates the possibility of inferring if a set of face images was used for fine-tuning a Latent…
The widespread availability of large-scale code datasets has fueled the rapid development of large language models (LLMs) for code-related tasks. These datasets may include sensitive personally identifiable information (PII), which can lead…
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…
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…
With the rapid advancements of large-scale text-to-image diffusion models, various practical applications have emerged, bringing significant convenience to society. However, model developers may misuse the unauthorized data to train…
Memorization in Large Language Models (LLMs) poses privacy and security risks, as models may unintentionally reproduce sensitive or copyrighted data. Existing analyses focus on average-case scenarios, often neglecting the highly skewed…
Among all privacy attacks against Machine Learning (ML), membership inference attacks (MIA) attracted the most attention. In these attacks, the attacker is given an ML model and a data point, and they must infer whether the data point was…
Membership Inference attacks (MIAs) aim to predict whether a data sample was present in the training data of a machine learning model or not, and are widely used for assessing the privacy risks of language models. Most existing attacks rely…
Large vision-language models (VLLMs) exhibit promising capabilities for processing multi-modal tasks across various application scenarios. However, their emergence also raises significant data security concerns, given the potential…
Large Language Models (LLMs) excel in various domains but pose inherent privacy risks. Existing methods to evaluate privacy leakage in LLMs often use memorized prefixes or simple instructions to extract data, both of which well-alignment…
Privacy attacks, particularly membership inference attacks (MIAs), are widely used to assess the privacy of generative models for tabular synthetic data, including those with Differential Privacy (DP) guarantees. These attacks often exploit…
Large Language Models (LLMs) have a privacy concern because they memorize training data (including personally identifiable information (PII) like emails and phone numbers) and leak it during inference. A company can train an LLM on its…