Related papers: Rethinking Visual Privacy: A Compositional Privacy…
Modern Vision-Language Models (VLMs) pose significant individual-level privacy risks by linking fragmented multimodal data to identifiable individuals through hierarchical chain-of-thought reasoning. However, existing privacy benchmarks…
With an increasing number of users sharing information online, privacy implications entailing such actions are a major concern. For explicit content, such as user profile or GPS data, devices (e.g. mobile phones) as well as web services…
While specialized learning-based models have historically dominated image privacy prediction, the current literature increasingly favours adopting large Vision-Language Models (VLMs) designed for generic tasks. This trend risks overlooking…
Visual attribute imbalance is a common yet underexplored issue in image classification, significantly impacting model performance and generalization. In this work, we first define the first-level and second-level attributes of images and…
As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognize and appropriately handle privacy-sensitive content is essential. We conduct a comprehensive evaluation of ten…
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…
Many video classification applications require access to personal data, thereby posing an invasive security risk to the users' privacy. We propose a privacy-preserving implementation of single-frame method based video classification with…
Cyber-physical systems (CPS) data privacy protection during sharing, aggregating, and publishing is a challenging problem. Several privacy protection mechanisms have been developed in the literature to protect sensitive data from…
We introduce the Visual Personalization Turing Test (VPTT), a new paradigm for evaluating contextual visual personalization based on perceptual indistinguishability, rather than identity replication. A model passes the VPTT if its output…
Recent advances in AI-powered surveillance have intensified concerns over the collection and processing of sensitive personal data. In response, research has increasingly focused on privacy-by-design solutions, raising the need for…
Traditional security mechanisms isolate resources from users who should not access them. We reflect the compositional nature of such security mechanisms back into the structure of LLMs to build a provably secure LLM; that we term SecureLLM.…
Vision and language models (VLMs) such as CLIP have showcased remarkable zero-shot recognition abilities yet face challenges in visio-linguistic compositionality, particularly in linguistic comprehension and fine-grained image-text…
The rise of social networking platforms has amplified privacy threats as users increasingly share sensitive information across profiles, content, and social connections. We present a Comprehensive Privacy Risk Scoring (CPRS) framework that…
As visual assistant systems powered by visual language models (VLMs) become more prevalent, concerns over user privacy have grown, particularly for blind and low vision users who may unknowingly capture personal private information in their…
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…
Augmented reality (AR) systems pose unique privacy risks due to their continuous capture of visual data. Existing AR privacy frameworks lack semantic understanding of visual content, limiting their effectiveness in detecting…
Conformal prediction (CP) provides sets of candidate classes with a guaranteed probability of containing the true class. However, it typically relies on a calibration set with clean labels. We address privacy-sensitive scenarios where the…
Vision is the most important sense for people, and it is also one of the main ways of cognition. As a result, people tend to utilize visual content to capture and share their life experiences, which greatly facilitates the transfer of…
Privacy is a complex, subjective and contextual concept that is difficult to define. Therefore, the annotation of images to train privacy classifiers is a challenging task. In this paper, we analyse privacy classification datasets and the…
Recent advances in multi-modal Large Language Models (M-LLMs) have demonstrated a powerful ability to synthesize implicit information from disparate sources, including images and text. These resourceful data from social media also introduce…