Related papers: Synthetic Data Can Mislead Evaluations: Membership…

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…

A Membership Inference Attack (MIA) assesses how much a target machine learning model reveals about its training data by determining whether specific query instances were part of the training set. State-of-the-art MIAs rely on training…

Synthetic data generation plays an important role in enabling data sharing, particularly in sensitive domains like healthcare and finance. Recent advances in diffusion models have made it possible to generate realistic, high-quality tabular…

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…

Although membership inference attacks (MIAs) and machine-generated text detection target different goals, their methods often exploit similar signals based on a language model's probability distribution, and the two tasks have been studied…

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.…

The widespread adoption of synthetic data raises new questions about how models generating the data can influence other large language models (LLMs) via distilled data. To start, our work exhaustively characterizes the impact of passive…

An over-the-air membership inference attack (MIA) is presented to leak private information from a wireless signal classifier. Machine learning (ML) provides powerful means to classify wireless signals, e.g., for PHY-layer authentication. As…

Large Language Models (LLMs) are increasingly deployed to enable or improve a multitude of real-world applications. Given the large size of their training data sets, their tendency to memorize training data raises serious privacy and…

Video large language models (VideoLLMs) are increasingly trained or instruction-tuned on large-scale video--text corpora collected from heterogeneous sources, raising an immediate privacy question: can an external auditor determine whether…

The increasing use of synthetic data generated by Large Language Models (LLMs) presents both opportunities and challenges in data-driven applications. While synthetic data provides a cost-effective, scalable alternative to real-world data…

Membership inference attacks (MIAs) pose a critical privacy threat to fine-tuned large language models (LLMs), especially when models are adapted to domain-specific tasks using sensitive data. While prior black-box MIA techniques rely on…

Vision-Language Models (VLMs), built on pre-trained vision encoders and large language models (LLMs), have shown exceptional multi-modal understanding and dialog capabilities, positioning them as catalysts for the next technological…

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…

Synthetic tabular data has gained attention for enabling privacy-preserving data sharing. While substantial progress has been made in single-table synthetic generation where data are modeled at the row or item level, most real-world data…

The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods, particularly heuristic-based divergence attacks, often exhibit limited success and offer…

Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy. In particular, fine-tuned models are highly vulnerable, as they are often fine-tuned on small and…

Test collections are crucial for evaluating Information Retrieval (IR) systems. Creating a diverse set of user queries for these collections can be challenging, and obtaining relevance judgments, which indicate how well retrieved documents…

Membership inference attacks (MIAs) aim to determine whether specific data were used to train a model. While extensively studied on classification models, their impact on time series forecasting remains largely unexplored. We address this…

The vulnerability of the Lottery Ticket Hypothesis has not been studied from the purview of Membership Inference Attacks. Through this work, we are the first to empirically show that the lottery ticket networks are equally vulnerable to…