相关论文: Membership Inference Attacks against Large Audio L…

We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM) designed for robust auditory perception and instruction-following. Recent LALMs augment Large Language Models (LLMs) with auditory capabilities by training on…

A membership inference attack (MIA) against a machine-learning model enables an attacker to determine whether a given data record was part of the model's training data or not. In this paper, we provide an in-depth study of the phenomenon of…

Membership inference attacks (MIAs) pose a serious threat to the privacy of machine learning models by allowing adversaries to determine whether a specific data sample was included in the training set. Although federated learning (FL) is…

This paper presents how to leak private information from a wireless signal classifier by launching an over-the-air membership inference attack (MIA). As machine learning (ML) algorithms are used to process wireless signals to make decisions…

Machine learning models can leak private information about their training data. The standard methods to measure this privacy risk, based on membership inference attacks (MIAs), only check if a given data point \textit{exactly} matches a…

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…

Large Audio Language Models (LALMs) have significantly advanced audio understanding but introduce critical security risks, particularly through audio jailbreaks. While prior work has focused on English-centric attacks, we expose a far more…

In membership inference attacks (MIAs), an adversary observes the predictions of a model to determine whether a sample is part of the model's training data. Existing MIA defenses conceal the presence of a target sample through strong…

Membership inference attacks (MIAs) are popular methods for empirically assessing the leakage of sensitive information in the training data through models or statistics learned from the data. The MIA vulnerability is often evaluated through…

Recent studies have shown that deep learning models are vulnerable to membership inference attacks (MIAs), which aim to infer whether a data record was used to train a target model or not. To analyze and study these vulnerabilities, various…

In the age of agentic AI, the growing deployment of multi-modal models (MMs) has introduced new attack vectors that can leak sensitive training data in MMs, causing privacy leakage. This paper investigates a black-box privacy attack, i.e.,…

The increasing parameters and expansive dataset of large language models (LLMs) highlight the urgent demand for a technical solution to audit the underlying privacy risks and copyright issues associated with LLMs. Existing studies have…

Large language models (LLMs) are increasingly used to generate financial alpha signals, yet growing evidence shows that LLMs memorize historical financial data from their training corpora, producing spurious predictive accuracy that…

A number of recent works have demonstrated that API access to machine learning models leaks information about the dataset records used to train the models. Further, the work of \cite{somesh-overfit} shows that such membership inference…

Transfer learning, successful in knowledge translation across related tasks, faces a substantial privacy threat from membership inference attacks (MIAs). These attacks, despite posing significant risk to ML model's training data, remain…

Membership inference attacks (MIAs) aim to determine whether a data sample was included in a machine learning (ML) model's training set and have become the de facto standard for measuring privacy leakages in ML. We propose an evaluation…

The increasing prominence of deep learning applications and reliance on personalized data underscore the urgent need to address privacy vulnerabilities, particularly Membership Inference Attacks (MIAs). Despite numerous MIA studies,…

Latent diffusion models have achieved remarkable success in high-fidelity text-to-image generation, but their tendency to memorize training data raises critical privacy and intellectual property concerns. Membership inference attacks (MIAs)…

Multimodal large language models can exhibit text dominance, over-relying on linguistic priors instead of grounding predictions in non-text inputs. One example is large audio-language models (LALMs) where decisive audio evidence can be…

The high cost of model training makes it increasingly desirable to develop techniques for unlearning. These techniques seek to remove the influence of a training example without having to retrain the model from scratch. Intuitively, once a…