Related papers: On Reliability of Efficient Membership Inference V…
OpenLVLM-MIA is a new benchmark that highlights fundamental challenges in evaluating membership inference attacks (MIA) against large vision-language models (LVLMs). While prior work has reported high attack success rates, our analysis…
Retrieval-Augmented Generation (RAG) and Supervised Finetuning (SFT) have become the predominant paradigms for equipping Large Language Models (LLMs) with external knowledge for diverse, knowledge-intensive tasks. However, while such…
Membership Inference Attacks (MIAs) expose privacy risks by determining whether a specific sample was part of a model's training set. These threats are especially serious in sensitive domains such as healthcare and finance. Traditional…
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…
Training a machine learning model with data following a meaningful order, i.e., from easy to hard, has been proven to be effective in accelerating the training process and achieving better model performance. The key enabling technique is…
Transfer learning (TL) has been demonstrated to improve DNN model performance when faced with a scarcity of training samples. However, the suitability of TL as a solution to reduce vulnerability of overfitted DNNs to privacy attacks is…
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…
While location data is extremely valuable for various applications, disclosing it prompts serious threats to individuals' privacy. To limit such concerns, organizations often provide analysts with aggregate time-series that indicate, e.g.,…
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…
The proliferation of large language models (LLMs) in the real world has come with a rise in copyright cases against companies for training their models on unlicensed data from the internet. Recent works have presented methods to identify if…
Tabular data synthesis using diffusion models has gained significant attention for its potential to balance data utility and privacy. However, existing privacy evaluations often rely on heuristic metrics or weak membership inference attacks…
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…
Membership inference attacks (MIAs) against machine learning models can lead to serious privacy risks for the training dataset used in the model training. In this paper, we propose a novel and effective Neuron-Guided Defense method named…
Cognitive diagnosis models (CDMs) are pivotal for creating fine-grained learner profiles in modern intelligent education platforms. However, these models are trained on sensitive student data, raising significant privacy concerns. While…
Most existing membership inference attacks (MIAs) utilize metrics (e.g., loss) calculated on the model's final state, while recent advanced attacks leverage metrics computed at various stages, including both intermediate and final stages,…
Image AutoRegressive generation has emerged as a new powerful paradigm with image autoregressive models (IARs) matching state-of-the-art diffusion models (DMs) in image quality (FID: 1.48 vs. 1.58) while allowing for a higher generation…
Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…
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…
Federated learning (FL) has emerged as a promising privacy-aware paradigm that allows multiple clients to jointly train a model without sharing their private data. Recently, many studies have shown that FL is vulnerable to membership…
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…