Related papers: From See to Shield: ML-Assisted Fine-Grained Acces…

Large language models (LLMs) are increasingly applied in fields such as finance, education, and governance due to their ability to generate human-like text and adapt to specialized tasks. However, their widespread adoption raises critical…

Fine-grained visual classification is a challenging task that recognizes the sub-classes belonging to the same meta-class. Large inter-class similarity and intra-class variance is the main challenge of this task. Most exiting methods try to…

Few-shot object detection (FSOD) aims at extending a generic detector for novel object detection with only a few training examples. It attracts great concerns recently due to the practical meanings. Meta-learning has been demonstrated to be…

The proliferation of visual sensors in smart home environments, particularly through wearable devices like smart glasses, introduces profound privacy challenges. Existing privacy controls are often static and coarse-grained, failing to…

Fine-grained hashing has become a powerful solution for rapid and efficient image retrieval, particularly in scenarios requiring high discrimination between visually similar categories. To enable each hash bit to correspond to specific…

Several researchers have proposed solutions for secure data outsourcing on the public clouds based on encryption, secret-sharing, and trusted hardware. Existing approaches, however, exhibit many limitations including high computational…

The enforcement of sensitive policies in untrusted environments is still an open challenge for policy-based systems. On the one hand, taking any appropriate security decision requires access to these policies. On the other hand, if such…

Organizations use data lakes to store and analyze sensitive data. But hackers may compromise data lake storage to bypass access controls and access sensitive data. To address this, we propose Membrane, a system that (1) cryptographically…

The study aims the development of a wearable device to combat the onslaught of covid-19. Likewise, to enhance the regular face shield available in the market. Furthermore, to raise awareness of the health and safety protocols initiated by…

The widespread deployment of text-to-image models is challenged by their potential to generate harmful content. While existing safety methods, such as prompt rewriting or model fine-tuning, provide valuable interventions, they often…

Self-supervised learning (SSL) has emerged as a powerful strategy for representation learning under limited annotation regimes, yet its effectiveness remains highly sensitive to many factors, especially the nature of the target task. In…

Existing image-to-image transformation approaches primarily focus on synthesizing visually pleasing data. Generating images with correct identity labels is challenging yet much less explored. It is even more challenging to deal with image…

Data spaces represent an emerging paradigm that facilitates secure and trusted data exchange through foundational elements of data interoperability, sovereignty, and trust. Within a data space, data items, potentially owned by different…

A well-designed fine-grained categorization system usually has three contradictory requirements: accuracy (the ability to identify objects among subordinate categories); interpretability (the ability to provide human-understandable…

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential…

We consider the problem of efficiently managing massive data in a large-scale distributed environment. We consider data strings of size in the order of Terabytes, shared and accessed by concurrent clients. On each individual access, a…

In this paper, we propose an access control method with a secret key for semantic segmentation models for the first time so that unauthorized users without a secret key cannot benefit from the performance of trained models. The method…

We present an interpretable deep model for fine-grained visual recognition. At the core of our method lies the integration of region-based part discovery and attribution within a deep neural network. Our model is trained using image-level…

Coordination of view coverage via privacy-aware smart cameras is key to a more socially responsible urban intelligence. Rather than maximizing view coverage at any cost or over relying on expensive cryptographic techniques, we address how…

Cloud computing has changed the way enterprises store, access and share data. Data is constantly being uploaded to the cloud and shared within an organization built on a hierarchy of many different individuals that are given certain data…