Related papers: DEMIS: A Threat Model for Selectively Encrypted Vi…
Self-supervised learning (SSL) is pervasively exploited in training high-quality upstream encoders with a large amount of unlabeled data. However, it is found to be susceptible to backdoor attacks merely via polluting a small portion of…
Virtual reality (VR) has emerged as a powerful tool for evaluating school security measures in high-risk scenarios such as school shootings, offering experimental control and high behavioral fidelity. However, assessing new interventions in…
With an increase in mobile and camera devices' popularity, digital content in the form of images has increased drastically. As personal life is being continuously documented in pictures, the risk of losing it to eavesdroppers is a matter of…
Numerous safety- or security-critical systems depend on cameras to perceive their surroundings, further allowing artificial intelligence (AI) to analyze the captured images to make important decisions. However, a concerning attack vector…
Gradient inversion attacks pose significant privacy threats to distributed training frameworks such as federated learning, enabling malicious parties to reconstruct sensitive local training data from gradient communications between clients…
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…
This paper proposes a novel visual model for web applications security monitoring. Although an automated intrusion detection system can shield a web application from common attacks, it usually cannot detect more complicated break-ins. So, a…
Recent years have witnessed remarkable progress in developing Vision-Language Models (VLMs) capable of processing both textual and visual inputs. These models have demonstrated impressive performance, leading to their widespread adoption in…
Deep learning has gained tremendous success and great popularity in the past few years. However, deep learning systems are suffering several inherent weaknesses, which can threaten the security of learning models. Deep learning's wide use…
Securing multimedia data has become of utmost importance especially in the applications related to military purposes. With the rise in development in computer and internet technology, multimedia data has become the most convenient method…
In this paper, we propose a novel generative model-based attack on learnable image encryption methods proposed for privacy-preserving deep learning. Various learnable encryption methods have been studied to protect the sensitive visual…
In this paper we study a cybersecurity problem of protecting system's secrets with multiple protections and a required security level, while minimizing the associated cost due to implementation/maintenance of these protections as well as…
This article investigates the security issue caused by false data injection attacks in distributed estimation, wherein each sensor can construct two types of residues based on local estimates and neighbor information, respectively. The…
Vision-Language Models (VLMs) have gained considerable prominence in recent years due to their remarkable capability to effectively integrate and process both textual and visual information. This integration has significantly enhanced…
Model Inversion (MI) attacks, which reconstruct the training dataset of neural networks, pose significant privacy concerns in machine learning. Recent MI attacks have managed to reconstruct realistic label-level private data, such as the…
In this paper we study a security problem of protecting secrets with multiple protections and minimum costs. The target system is modeled as a discrete-event system (DES) in which a few states are secrets, and there are multiple subsets of…
In this study, we analyze model inversion attacks with only two assumptions: feature vectors of user data are known, and a black-box API for inference is provided. On the one hand, limitations of existing studies are addressed by opting for…
Video Instance Segmentation (VIS) jointly tackles multi-object detection, tracking, and segmentation in video sequences. In the past, VIS methods mirrored the fragmentation of these subtasks in their architectural design, hence missing out…
Visual sensors serve as a critical component of the Internet of Things (IoT). There is an ever-increasing demand for broad applications and higher resolutions of videos and cameras in smart homes and smart cities, such as in security…
Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…