CybAI news

arXiv:2411.14565v1 Announce Type: new Abstract: Video Anomaly Detection (VAD) aims to automatically analyze spatiotemporal patterns in surveillance videos collected from open spaces to detect anomalous events that may cause harm without physical contact. However, vision-based surveillance systems such as closed-circuit television often capture personally identifiable information. The lack of transparency and interpretability in video transmission and usage raises public concerns about privacy and ethics, limiting the real-world application of VAD. Recently, researchers have focused on privacy concerns in VAD by conducting systematic studies from various perspectives including data, features, and systems, making Privacy-Preserving Video Anomaly Detection (P2VAD) a hotspot in…

[Submitted on 9 May 2024 (v1), last revised 21 Nov 2024 (this version, v2)] View a PDF of the paper titled Large Language Models Show Human-like Social Desirability Biases in Survey Responses, by Aadesh Salecha and 5 other authors View PDF HTML (experimental) Abstract:As Large Language Models (LLMs) become widely used to model and simulate human behavior, understanding their biases becomes critical. We developed an experimental framework using Big Five personality surveys and uncovered a previously undetected social desirability bias in a wide range of LLMs. By systematically varying the number of questions LLMs were exposed to, we demonstrate their…

We are excited to announce that Azure Private Link is now Generally Available (GA) for Databricks serverless and Mosaic AI Model Serving workloads! Now you can enable private connectivity from Databricks SQL, Jobs, Notebooks, Delta Live Tables, and Mosaic AI Model Serving CPU/GPU endpoints to your Azure Data Lake Storage (ADLS) and managed Azure resources. Today we are also introducing new support for 60+ Azure 1st party resources, such as Azure OpenAI and Azure SQL, which expands on our announcement earlier this year of private link support for DBSQL warehouses to Azure Storage. Azure Private Link provides a direct, secure…

arXiv:2411.14612v1 Announce Type: new Abstract: Hyperdimensional computing (HDC) enables efficient data encoding and processing in high-dimensional space, benefiting machine learning and data analysis. However, underutilization of these spaces can lead to overfitting and reduced model reliability, especially in data-limited systems a critical issue in sectors like healthcare that demand robustness and consistent performance. We introduce BoostHD, an approach that applies boosting algorithms to partition the hyperdimensional space into subspaces, creating an ensemble of weak learners. By integrating boosting with HDC, BoostHD enhances performance and reliability beyond existing HDC methods. Our analysis highlights the importance of efficient utilization of hyperdimensional spaces…