Related papers: Rethinking Visual Privacy: A Compositional Privacy…
Privacy-preservation for sensitive data has become a challenging issue in cloud computing. Threat modeling as a part of requirements engineering in secure software development provides a structured approach for identifying attacks and…
Accurately predicting whether an image is private before sharing it online is difficult due to the vast variety of content and the subjective nature of privacy itself. In this paper, we evaluate privacy models that use objects extracted…
Differential privacy (DP) provides a mathematical guarantee limiting what an adversary can learn about any individual from released data. However, achieving this protection typically requires adding noise, and noise can accumulate when many…
Our research reveals a new privacy risk associated with the vision-language model (VLM) agentic framework: the ability to infer sensitive attributes (e.g., age and health information) and even abstract ones (e.g., personality and social…
Data serves as the fundamental foundation for advancing deep learning, particularly tabular data presented in a structured format, which is highly conducive to modeling. However, even in the era of LLM, obtaining tabular data from sensitive…
Sharing images online poses security threats to a wide range of users due to the unawareness of privacy information. Deep features have been demonstrated to be a powerful representation for images. However, deep features usually suffer from…
Lensless imaging can provide visual privacy due to the highly multiplexed characteristic of its measurements. However, this alone is a weak form of security, as various adversarial attacks can be designed to invert the one-to-many scene…
Differential privacy (DP) has become the de facto standard for protecting sensitive data, providing strong guarantees that published statistics or models reveal limited information about any individual. However, privacy noise and restricted…
In this paper, we propose a privacy-preserving image classification method that is based on the combined use of encrypted images and the vision transformer (ViT). The proposed method allows us not only to apply images without visual…
People may be unaware of the privacy risks of uploading an image online. In this paper, we present Graph Privacy Advisor, an image privacy classifier that uses scene information and object cardinality as cues to predict whether an image is…
Text-to-image generation models have recently attracted unprecedented attention as they unlatch imaginative applications in all areas of life. However, developing such models requires huge amounts of data that might contain…
We consider vertical logistic regression (VLR) trained with mini-batch gradient descent -- a setting which has attracted growing interest among industries and proven to be useful in a wide range of applications including finance and medical…
Compositional Reasoning (CR) entails grasping the significance of attributes, relations, and word order. Recent Vision-Language Models (VLMs), comprising a visual encoder and a Large Language Model (LLM) decoder, have demonstrated…
Image degradations can occur during acquisition, processing, and transmission, altering visual appearance and affecting downstream vision tasks. They are studied in several communities, including synthetic corruption benchmarks for…
Differential privacy (DP) is typically formulated as a worst-case privacy guarantee over all individuals in a database. More recently, extensions to individual subjects or their attributes, have been introduced. Under the…
Synthetic data is often presented as a method for sharing sensitive information in a privacy-preserving manner by reproducing the global statistical properties of the original data without disclosing sensitive information about any…
While significant progress has been made in conventional fairness-aware machine learning (ML) and differentially private ML (DPML), the fairness of privacy protection across groups remains underexplored. Existing studies have proposed…
The proliferation of Vision-Language Models (VLMs) introduces profound privacy risks from personal videos. This paper addresses the critical yet unexplored inferential privacy threat, the risk of inferring sensitive personal attributes over…
Multimodal contrastive learning models (e.g., CLIP) can learn high-quality representations from large-scale image-text datasets, while they exhibit significant vulnerabilities to backdoor attacks, raising serious safety concerns. In this…
Personalized concept generation by tuning diffusion models with a few images raises potential legal and ethical concerns regarding privacy and intellectual property rights. Researchers attempt to prevent malicious personalization using…