Related papers: MRMMIA: Membership Inference Attacks on Memory in …
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…
The lack of data transparency in Large Language Models (LLMs) has highlighted the importance of Membership Inference Attack (MIA), which differentiates trained (member) and untrained (non-member) data. Though it shows success in previous…
Large Language Models (LLMs) utilize large amounts of data for their training, some of which may come from copyrighted sources. Membership Inference Attacks (MIA) aim to detect those documents and whether they have been included in the…
We demonstrate how a target model's generalization gap leads directly to an effective deterministic black box membership inference attack (MIA). This provides an upper bound on how secure a model can be to MIA based on a simple metric.…
This paper introduces a novel approach to membership inference attacks (MIA) targeting stable diffusion computer vision models, specifically focusing on the highly sophisticated Stable Diffusion V2 by StabilityAI. MIAs aim to extract…
Membership inference attacks (MIAs) on code completion models offer an effective way to assess privacy risks by inferring whether a given code snippet was part of the training data. Existing black- and gray-box MIAs rely on expensive…
Membership inference attacks (MIAs) infer whether a specific data record is used for target model training. MIAs have provoked many discussions in the information security community since they give rise to severe data privacy issues,…
Membership inference attacks (MIAs) have become the standard tool for evaluating privacy leakage in machine learning (ML). Among them, the Likelihood-Ratio Attack (LiRA) is widely regarded as the state of the art when sufficient shadow…
The rapid advancement of diffusion-based image generation models has raised serious concerns regarding potential copyright and privacy infringements involving human-created data. Membership inference attacks (MIAs) have emerged as a…
Membership inference attacks (MIAs) pose a critical threat to the privacy of training data in deep learning. Despite significant progress in attack methodologies, our understanding of when and how models encode membership information during…
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…
Machine unlearning (MU) has emerged as a key mechanism for ensuring data privacy and regulatory compliance by enabling models to forget specific training samples. However, recent studies have shown that the removal of data can inadvertently…
Multimodal retrieval-augmented generation (RAG) systems enhance large vision-language models by integrating cross-modal knowledge, enabling their increasing adoption across real-world multimodal tasks. These knowledge databases may contain…
Membership Inference Attacks (MIAs) have emerged as a valuable framework for evaluating privacy leakage by machine learning models. Score-based MIAs are distinguished, in particular, by their ability to exploit the confidence scores that…
Diffusion models have achieved tremendous success in image generation, but they also raise significant concerns regarding privacy and copyright issues. Membership Inference Attacks (MIAs) are designed to ascertain whether specific data was…
Small language models (SLMs) are increasingly valued for their efficiency and deployability in resource-constrained environments, making them useful for on-device, privacy-sensitive, and edge computing applications. On the other hand,…
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…
Large Reasoning Models (LRMs) have rapidly gained prominence for their strong performance in solving complex tasks. Many modern black-box LRMs expose the intermediate reasoning traces through APIs to improve transparency (e.g., Gemini-2.5…
Large language models (LLMs) are increasingly deployed in interactive and retrieval-augmented settings, raising significant privacy concerns. While attacks such as Membership Inference (MIA), Attribute Inference (AIA), Data Extraction…
While Membership Inference Attacks (MIAs) are the prevailing method for identifying training data, their application has expanded into privacy auditing and machine unlearning. Nevertheless, the field lacks a systematic framework for…