相关论文: Automatic Calibration for Membership Inference Att…

Membership inference attacks (MIAs) on diffusion models have emerged as potential evidence of unauthorized data usage in training pre-trained diffusion models. These attacks aim to detect the presence of specific images in training datasets…

Retrieval Augmented Generation (RAG) systems have shown great promise in natural language processing. However, their reliance on data stored in a retrieval database, which may contain proprietary or sensitive information, introduces new…

The increased availability of genetic data has transformed genomics research, but raised many privacy concerns regarding its handling due to its sensitive nature. This work explores the use of language models (LMs) for the generation of…

Retrieval-Augmented Generation (RAG) is a state-of-the-art technique that mitigates issues such as hallucinations and knowledge staleness in Large Language Models (LLMs) by retrieving relevant knowledge from an external database to assist…

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…

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…

Learned recommender systems may inadvertently leak information about their training data, leading to privacy violations. We investigate privacy threats faced by recommender systems through the lens of membership inference. In such attacks,…

Membership Inference Attacks (MIA) enable to empirically assess the privacy of a machine learning algorithm. In this paper, we propose TAMIS, a novel MIA against differentially-private synthetic data generation methods that rely on…

Aligning large language models (LLMs) to diverse human preferences is fundamentally challenging since criteria can often conflict with each other. Inference-time alignment methods have recently gained popularity as they allow LLMs to be…

All prior membership inference attacks for fine-tuned language models use hand-crafted heuristics (e.g., loss thresholding, Min-K\%, reference calibration), each bounded by the designer's intuition. We introduce the first transferable…

Tabular data sharing under privacy constraints is increasingly important for research and collaboration. Synthetic data generators (SDGs) are a promising solution, but synthetic data remains vulnerable to attacks, such as membership…

As large language models (LLMs) become progressively more embedded in clinical decision-support, documentation, and patient-information systems, ensuring their privacy and trustworthiness has emerged as an imperative challenge for the…

Federated Learning (FL) is an emerging solution to the data scarcity problem for training deep learning models in hardware assurance. While FL is designed to enhance privacy by not sharing raw data, it remains vulnerable to Membership…

Membership inference attacks (MIAs) aim to determine whether a sample was part of a model's training set, posing serious privacy risks for modern machine-learning systems. Existing MIAs primarily rely on static indicators, such as loss or…

Diffusion-based generative models have shown great potential for image synthesis, but there is a lack of research on the security and privacy risks they may pose. In this paper, we investigate the vulnerability of diffusion models to…

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…

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…

Despite explicit alignment efforts for large language models (LLMs), they can still be exploited to trigger unintended behaviors, a phenomenon known as "jailbreaking." Current jailbreak attack methods mainly focus on discrete prompt…

The integration of machine learning (ML) in numerous critical applications introduces a range of privacy concerns for individuals who provide their datasets for model training. One such privacy risk is Membership Inference (MI), in which an…

Large Language Models are increasingly deployed for decision-making, yet their adoption in high-stakes domains remains limited by miscalibrated probabilities, unfaithful explanations, and inability to incorporate expert knowledge precisely.…