Related papers: From See to Shield: ML-Assisted Fine-Grained Acces…
Supervisory Control and Data Acquisition (SCADA) systems support and control the operation of many critical infrastructures that our society depend on, such as power grids. Since SCADA systems become a target for cyber attacks and the…
Quality control is a critical aspect of manufacturing, particularly in ensuring the proper assembly of small components in production lines. Existing solutions often rely on single-view imaging or manual inspection, which are prone to…
There are many well-known techniques to secure sensed data in IoT/CPS systems, e.g., by authenticating communication end-points, encrypting data before transmission, and obfuscating traffic patterns. Such techniques protect sensed data from…
Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data. Although there has been remarkable recent progress, the scope of demonstration in SSL has mainly been on…
Video privacy leakage is becoming an increasingly severe public problem, especially in cloud-based video surveillance systems. It leads to the new need for secure cloud-based video applications, where the video is encrypted for privacy…
The Feature Pyramid Network (FPN) presents a remarkable approach to alleviate the scale variance in object representation by performing instance-level assignments. Nevertheless, this strategy ignores the distinct characteristics of…
Differentially private (DP) image synthesis aims to generate synthetic images from a sensitive dataset, alleviating the privacy leakage concerns of organizations sharing and utilizing synthetic images. Although previous methods have…
Deep learning-based fine-grained network intrusion detection systems (NIDS) enable different attacks to be responded to in a fast and targeted manner with the help of large-scale labels. However, the cost of labeling causes insufficient…
Model repositories such as Hugging Face increasingly distribute machine learning artifacts serialized with Python's pickle format, exposing users to remote code execution (RCE) risks during model loading. Recent defenses, such as…
Visual Cryptography comes under cryptography domain. It deals with encrypting and decrypting of visual information like pictures, texts, videos $ etc.$ Multi Secret Image Sharing (MSIS) scheme is a part of visual cryptography that provides…
Detection of small objects and objects far away in the scene is a major challenge in surveillance applications. Such objects are represented by small number of pixels in the image and lack sufficient details, making them difficult to detect…
Human skin segmentation is a crucial task in computer vision and biometric systems, yet it poses several challenges such as variability in skin color, pose, and illumination. This paper presents a robust data-driven skin segmentation method…
Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in…
In this cloud-dependent era, various security techniques, such as encryption, steganography, and hybrid approaches, have been utilized in cloud computing to enhance security, maintain enormous storage capacity, and provide ease of access.…
Classical pixel-based Visual Servoing (VS) approaches offer high accuracy but suffer from a limited convergence area due to optimization nonlinearity. Modern deep learning-based VS methods overcome traditional vision issues but lack…
Adversarial attacks expose a fundamental vulnerability in modern deep vision models by exploiting their dependence on dense, pixel-level representations that are highly sensitive to imperceptible perturbations. Traditional defense…
Large-scale fine-grained image retrieval has two main problems. First, low dimensional feature embedding can fasten the retrieval process but bring accuracy reduce due to overlooking the feature of significant attention regions of images in…
This work presents a novel protocol for fast secure inference of neural networks applied to computer vision applications. It focuses on improving the overall performance of the online execution by deploying a subset of the model weights in…
The problem of high-dimensional and large-scale representation of visual data is addressed from an unsupervised learning perspective. The emphasis is put on discrete representations, where the description length can be measured in bits and…
Internet of Things is growing rapidly, with many connected devices now available to consumers. With this growth, the IoT apps that manage the devices from smartphones raise significant security concerns. Typically, these apps are secured…