Related papers: DEMIS: A Threat Model for Selectively Encrypted Vi…
In this work, we present a new computer vision task named video object of interest segmentation (VOIS). Given a video and a target image of interest, our objective is to simultaneously segment and track all objects in the video that are…
Phishing attacks pose a significant threat to Internet users, with cybercriminals elaborately replicating the visual appearance of legitimate websites to deceive victims. Visual similarity-based detection systems have emerged as an…
Deploying large vision-language models (LVLMs) introduces a unique vulnerability: susceptibility to malicious attacks via visual inputs. However, existing defense methods suffer from two key limitations: (1) They solely focus on textual…
Continued ubiquity of communication infrastructure across Internet of Things (IoT) ecosystems has seen persistent advances of dynamic, intelligent, virtualised sensing and actuation. This has led to effective interaction across the…
With rich visual data, such as images, becoming readily associated with items, visually-aware recommendation systems (VARS) have been widely used in different applications. Recent studies have shown that VARS are vulnerable to item-image…
The increase of cyber attacks in both the numbers and varieties in recent years demands to build a more sophisticated network intrusion detection system (NIDS). These NIDS perform better when they can monitor all the traffic traversing…
The revolution in computer hardware, especially in graphics processing units and tensor processing units, has enabled significant advances in computer graphics and artificial intelligence algorithms. In addition to their many beneficial…
Cryptocurrencies have emerged as a new form of digital money that has not escaped the eyes of cyber-attackers. Traditionally, they have been maliciously used as a medium of exchange for proceeds of crime in the cyber dark-market by…
A novel method for access control with a secret key is proposed to protect models from unauthorized access in this paper. We focus on semantic segmentation models with the vision transformer (ViT), called segmentation transformer (SETR).…
Due to the advances of sensing and storage technologies, a tremendous amount of data becomes available and, it supports the phenomenal growth of artificial intelligence (AI) techniques especially, deep learning (DL), in various application…
In large-scale networks, communication links between nodes are easily injected with false data by adversaries. This paper proposes a novel security defense strategy from the perspective of attack detection scheduling to ensure the security…
Video surveillance systems have been installed to ensure the student safety in schools. However, discovering dangerous behaviors, such as fighting and falling down, usually depends on untimely human observations. In this paper, we focus on…
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.…
Over the years, IP Multimedia Subsystems (IMS) networks have become increasingly critical as they form the backbone of modern telecommunications, enabling the integration of multimedia services such as voice, video, and messaging over…
Data security is required when communications over untrusted networks takes place. Security tools such as cryptography and steganography are applied to achieve such objectives, but both have limitations and susceptible to attacks if they…
Deep neural networks have empowered accurate device-free human activity recognition, which has wide applications. Deep models can extract robust features from various sensors and generalize well even in challenging situations such as…
Cybersecurity practices require effort to be maintained, and one weakness is a lack of awareness regarding potential attacks not only in the usage of machine learning models, but also in their development process. Previous studies have…
In recent years Deep Neural Networks (DNNs) have achieved remarkable results and even showed super-human capabilities in a broad range of domains. This led people to trust in DNNs' classifications and resulting actions even in…
We analyze the security of recently proposed image encryption scheme [1]. We show that the scheme is insecure and the methods used to evaluate its security are insufficient. By designing the Deliberately Weak Cipher, a completely vulnerable…
Deep Learning has recently become hugely popular in machine learning, providing significant improvements in classification accuracy in the presence of highly-structured and large databases. Researchers have also considered privacy…