相关论文: Do Vision-Language Models Leak What They Learn? Ad…

Model inversion (MI) attacks aim to infer and reconstruct private training data by abusing access to a model. MI attacks have raised concerns about the leaking of sensitive information (e.g. private face images used in training a face…

Vision-Language Models (VLMs) combine visual and textual understanding, rendering them well-suited for diverse tasks like generating image captions and answering visual questions across various domains. However, these capabilities are built…

Deep Neural Networks (DNNs) have revolutionized various domains with their exceptional performance across numerous applications. However, Model Inversion (MI) attacks, which disclose private information about the training dataset by abusing…

As large language models (LLMs) become ubiquitous in our daily tasks and digital interactions, associated privacy risks are increasingly in focus. While LLM privacy research has primarily focused on the leakage of model training data, it…

Model inversion (MI) attacks are aimed at reconstructing training data from model parameters. Such attacks have triggered increasing concerns about privacy, especially given a growing number of online model repositories. However, existing…

Model Inversion (MI) attacks aim to reconstruct private training data by abusing access to machine learning models. Contemporary MI attacks have achieved impressive attack performance, posing serious threats to privacy. Meanwhile, all…

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.,…

Model Inversion attacks aim to reconstruct information from private training data by exploiting access to a target model. Nearly all recent MI studies evaluate attack success using a standard framework that computes attack accuracy through…

Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VLMs exhibit significant vulnerability against adversarial…

Recent studies have shown that distributed machine learning is vulnerable to gradient inversion attacks, where private training data can be reconstructed by analyzing the gradients of the models shared in training. Previous attacks…

Vision classifiers are often trained on proprietary datasets containing sensitive information, yet the models themselves are frequently shared openly under the privacy-preserving assumption. Although these models are assumed to protect…

Large language models (LLMs) have transformed natural language processing, but their ability to memorize training data poses significant privacy risks. This paper investigates model inversion attacks on the Llama 3.2 model, a multilingual…

Recent advances in visual-language alignment have endowed vision-language models (VLMs) with fine-grained image understanding capabilities. However, this progress also introduces new privacy risks. This paper first proposes a novel privacy…

The success of deep neural networks has driven numerous research studies and applications from Euclidean to non-Euclidean data. However, there are increasing concerns about privacy leakage, as these networks rely on processing private data.…

Despite inheriting security measures from underlying language models, Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues. Through empirical analysis, we uncover two critical findings: scenario-matched images…

Large Language Models (LLMs), characterized by being trained on broad amounts of data in a self-supervised manner, have shown impressive performance across a wide range of tasks. Indeed, their generative abilities have aroused interest on…

Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the…

Model Inversion (MI), in which an adversary abuses access to a trained Machine Learning (ML) model attempting to infer sensitive information about its original training data, has attracted increasing research attention. During MI, the…

Recent years have witnessed remarkable progress in developing Vision-Language Models (VLMs) capable of processing both textual and visual inputs. These models have demonstrated impressive performance, leading to their widespread adoption in…

Decentralized training has become a resource-efficient framework to democratize the training of large language models (LLMs). However, the privacy risks associated with this framework, particularly due to the potential inclusion of…