Virtual reality (VR) has advanced rapidly and is used for many entertainment and business purposes. The need for secure, transparent and non-intrusive identification mechanisms is important to facilitate users’ safe participation and secure experience. People are kinesiologically unique, having individual behavioral and movement characteristics, which can be leveraged and used in security sensitive VR applications to compensate for users’ inability to detect potential observational attackers in the physical world. Additionally, such method of identification using a user’s kinesiological data is valuable in common scenarios where multiple users simultaneously participate in a VR environment. In this paper, we present a user study (n = 15) where our participants performed a series of controlled tasks that require physical movements (such as grabbing, rotating and dropping) that could be decomposed into unique kinesiological patterns while we monitored and captured their hand, head and eye gaze data within the VR environment. We present an analysis of the data and show that these data can be used as a biometric discriminant of high confidence using machine learning classification methods such as kNN or SVM, thereby adding a layer of security in terms of identification or dynamically adapting the VR environment to the users’ preferences. We also performed a whitebox penetration testing with 12 attackers, some of whom were physically similar to the participants. We could obtain an average identification confidence value of 0.98 from the actual participants’ test data after the initial study and also a trained model classification accuracy of 98.6%. Penetration testing indicated all attackers resulted in confidence values of less than 50% (<50%), although physically similar attackers had higher confidence values. These findings can help the design and development of secure VR systems.

In recent years, high-performance video recording devices have become ubiquitous, posing an unprecedented challenge to preserving personal privacy. As a result, privacy-preserving video systems have been receiving increased attention. In this paper, we present a novel privacy-preserving video algorithm that uses semantic segmentation to identify regions of interest, which are then anonymized with an adaptive blurring algorithm. This algorithm addresses two of the most important shortcomings of existing solutions: it is multi-scale, meaning it can identify and uniformly anonymize objects of different scales in the same image, and it is class-generic, so it can be used to anonymize any class of objects of interest. We show experimentally that our algorithm achieves excellent anonymity while preserving meaning in the visual data processed.

Facial recognition tools are becoming exceptionally accurate in identifying people from images. However, this comes at the cost of privacy for users of online services with photo management (e.g. social media platforms). Particularly troubling is the ability to leverage unsupervised learning to recognize faces even when the user has not labeled their images. In this paper we propose Ulixes, a strategy to generate visually non-invasive facial noise masks that yield adversarial examples, preventing the formation of identifiable user clusters in the embedding space of facial encoders. This is applicable even when a user is unmasked and labeled images are available online. We demonstrate the effectiveness of Ulixes by showing that various classification and clustering methods cannot reliably label the adversarial examples we generate. We also study the effects of Ulixes in various black-box settings and compare it to the current state of the art in adversarial machine learning. Finally, we challenge the effectiveness of Ulixes against adversarially trained models and show that it is robust to countermeasures.

Despite rapid digitalization, agricultural computer vision still faces persistent data bottlenecks. The collection and annotation of field images are constrained by seasonality and biological variability, require domain expertise, must adapt to the perception and navigation conditions of ground robots, and are further limited by privacy and data-sharing concerns. Together, these factors restrict the scale, diversity, and transferability of real-world datasets. This paper provides a systematic review of two-dimensional (2D) and three-dimensional (3D) synthetic data generation (SDG) pipelines in agriculture. We outline 2D pipelines ranging from classical augmentation and compositing to learning-based generative models, and we review 3D approaches spanning procedural plant modeling, photorealistic rendering engines, customized simulation platforms, and reconstruction-based assets. This review focuses on 2D and 3D SDG for agricultural vision tasks (image acquisition, object detection, semantic and instance segmentation, and classification), including weed and disease management, phenotyping, yield management, precision livestock farming, aquaculture, and fruit management. Beyond cataloguing methods, we adopt a deployment-oriented perspective and present task-driven design rules: select SDG according to the primary bottleneck (class imbalance, occlusion, or domain shift); favor a "3D geometry first, 2D stylization later" workflow when geometric fidelity and visual realism must both be preserved; combine domain randomization or translation with limited target-domain fine-tuning; and align method choice with available expertise and computing resources. We also synthesize challenges related to realism and diversity, generalization and sim-to-real transfer, and ethical and legal considerations. For evaluation, we compile common practices, including expert plausibility checks, quantitative image metrics, and controlled comparisons on identical real-world test sets, complemented by ablation studies and statistical tests. Ultimately, the review integrates methodological, empirical, and deployment perspectives into a practical roadmap for selecting, building, and validating SDG pipelines that remain agronomically credible and transferable to real agricultural environments.

The popularity and projected growth of in-home smart speaker assistants, such as Amazon's Echo, has raised privacy concerns among consumers and privacy advocates. Notable questions regarding the collection and storage of user data by for-profit organizations include: what data is being collected and how is it being used, who has or can obtain access to such data, and how can user privacy be maintained while providing useful services. In addition to concerns regarding what the speaker manufacturer will do with your data, there are also more fundamental concerns about the security of these devices, third-party plugins, and the servers where they store recorded data. To address these privacy and security concerns, we introduce an intermediary device to provide an additional layer of security, which we call the \textit{smart, smart speaker blocker} or Smart\textsuperscript{2} for short. By intelligently filtering sensitive conversations, and completely blocking this information from reaching a smart speaker's microphone(s), the Smart$^2$ Speaker Blocker is an open-source, network-local (offline) smart device that provides users with decisive control over what data leaves their living room.

This paper introduces a novel approach to membership inference attacks (MIA) targeting stable diffusion computer vision models, specifically focusing on the highly sophisticated Stable Diffusion V2 by StabilityAI. MIAs aim to extract sensitive information about a model's training data, posing significant privacy concerns. Despite its advancements in image synthesis, our research reveals privacy vulnerabilities in the stable diffusion models' outputs. Exploiting this information, we devise a black-box MIA that only needs to query the victim model repeatedly. Our methodology involves observing the output of a stable diffusion model at different generative epochs and training a classification model to distinguish when a series of intermediates originated from a training sample or not. We propose numerous ways to measure the membership features and discuss what works best. The attack's efficacy is assessed using the ROC AUC method, demonstrating a 60\% success rate in inferring membership information. This paper contributes to the growing body of research on privacy and security in machine learning, highlighting the need for robust defenses against MIAs. Our findings prompt a reevaluation of the privacy implications of stable diffusion models, urging practitioners and developers to implement enhanced security measures to safeguard against such attacks.