相关论文: Membership Inference on LLMs in the Wild

Membership Inference Attacks (MIAs) are currently a dominant approach for evaluating privacy in machine learning applications. Despite their significance in identifying records belonging to the training dataset, several concerns remain…

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…

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…

The rapid advancement of Large Language Models (LLMs) has been driven by extensive datasets that may contain sensitive information, raising serious privacy concerns. One notable threat is the Membership Inference Attack (MIA), where…

Document Visual Question Answering (DocVQA) has introduced a new paradigm for end-to-end document understanding, and quickly became one of the standard benchmarks for multimodal LLMs. Automating document processing workflows, driven by…

Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership Inference Attacks (MIA) exploit it to obtain confidential information about the data used for…

Machine Learning (ML) has made unprecedented progress in the past several decades. However, due to the memorability of the training data, ML is susceptible to various attacks, especially Membership Inference Attacks (MIAs), the objective of…

Large language models (LLMs) are trained on massive corpora that may contain sensitive information, creating privacy risks under membership inference attacks (MIAs). Knowledge distillation is widely used to compress LLMs into smaller…

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…

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…

With the emergence of powerful large-scale foundation models, the training paradigm is increasingly shifting from from-scratch training to transfer learning. This enables high utility training with small, domain-specific datasets typical in…

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership…

Diffusion Language Models (DLMs) represent a promising alternative to autoregressive language models, using bidirectional masked token prediction. Yet their susceptibility to privacy leakage via Membership Inference Attacks (MIA) remains…

Large language models (LLMs) are increasingly augmented with long-term memory systems to overcome finite context windows and enable persistent reasoning across interactions. However, recent research finds that LLMs become more vulnerable…

Membership inference attacks (MIAs) against machine learning (ML) models aim to determine whether a given data point was part of the model training data. These attacks may pose significant privacy risks to individuals whose sensitive data…

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…

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,…

Machine learning models, in particular deep neural networks, are currently an integral part of various applications, from healthcare to finance. However, using sensitive data to train these models raises concerns about privacy and security.…

Membership inference attacks (MIAs) pose a significant threat to the privacy of machine learning models and are widely used as tools for privacy assessment, auditing, and machine unlearning. While prior MIA research has primarily focused on…

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.…