相关论文: Membership Inference Attacks against Large Vision-…

Membership Inference Attacks (MIAs) determine whether a specific data point was included in the training set of a target model. In this paper, we introduce the Semantic Membership Inference Attack (SMIA), a novel approach that enhances MIA…

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…

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…

Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored vulnerabilities. Existing multimodal red-teaming methods largely rely on brittle templates,…

Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities, yet their proficiency in understanding and reasoning over multiple images remains largely unexplored. While existing benchmarks have initiated the evaluation of…

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) can leak sensitive training data through memorization and membership inference attacks. Prior work has primarily focused on strong adversarial assumptions, including attacker access to entire samples or long,…

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…

Given the rising popularity of AI-generated art and the associated copyright concerns, identifying whether an artwork was used to train a diffusion model is an important research topic. The work approaches this problem from the membership…

The data used to train deep neural network (DNN) models in applications such as healthcare and finance typically contain sensitive information. A DNN model may suffer from overfitting. Overfitted models have been shown to be susceptible to…

Determining whether a dataset was part of a machine learning model's training data pool can reveal privacy vulnerabilities, a challenge often addressed through membership inference attacks (MIAs). Traditional MIAs typically require access…

Machine learning (ML) has become a core component of many real-world applications and training data is a key factor that drives current progress. This huge success has led Internet companies to deploy machine learning as a service (MLaaS).…

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 proliferation of powerful Text-to-Video (T2V) models, trained on massive web-scale datasets, raises urgent concerns about copyright and privacy violations. Membership inference attacks (MIAs) provide a principled tool for auditing such…

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.…

Today, the training of large language models (LLMs) can involve personally identifiable information and copyrighted material, incurring dataset misuse. To mitigate the problem of dataset misuse, this paper explores \textit{dataset…

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…

Vision-language models (VLMs) have revolutionized multimodal AI applications but introduce novel security vulnerabilities that remain largely unexplored. We present the first comprehensive study of steganographic prompt injection attacks…

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…

Vision-language artificial intelligence models (VLMs) possess medical knowledge and can be employed in healthcare in numerous ways, including as image interpreters, virtual scribes, and general decision support systems. However, here, we…