Related papers: MV-Gate: Insider Threat Detection via Multi-View B…

The latest trend in anomaly detection is to train a unified model instead of training a separate model for each category. However, existing multi-class anomaly detection (MCAD) models perform poorly in multi-view scenarios because they…

Abnormal event detection is a challenging task that requires effectively handling intricate features of appearance and motion. In this paper, we present an approach of detecting anomalies in videos by learning a novel LSTM based…

The analysis of multivariate time series data is challenging due to the various frequencies of signal changes that can occur over both short and long terms. Furthermore, standard deep learning models are often unsuitable for such datasets,…

In this paper, Gated-ViGAT, an efficient approach for video event recognition, utilizing bottom-up (object) information, a new frame sampling policy and a gating mechanism is proposed. Specifically, the frame sampling policy uses weighted…

High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predict harmful AI…

Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored vulnerabilities. Existing multimodal red-teaming methods largely rely on brittle templates,…

Recurrent neural networks with various types of hidden units have been used to solve a diverse range of problems involving sequence data. Two of the most recent proposals, gated recurrent units (GRU) and minimal gated units (MGU), have…

Recent advancements in generative AI, particularly in speech synthesis, have enabled the generation of highly natural-sounding synthetic speech that closely mimics human voices. While these innovations hold promise for applications like…

In image generation, Multiple Latent Variable Generative Models (MLVGMs) employ multiple latent variables to gradually shape the final images, from global characteristics to finer and local details (e.g., StyleGAN, NVAE), emerging as…

Advanced Persistent Threats (APTs) are difficult to detect due to their complexity and stealthiness. To mitigate such attacks, many approaches model entities and their relationship using provenance graphs to detect the stealthy and…

Vision-Language Models (VLMs), built on pre-trained vision encoders and large language models (LLMs), have shown exceptional multi-modal understanding and dialog capabilities, positioning them as catalysts for the next technological…

Activity profiles of terrorist groups show frequent spurts and downfalls corresponding to changes in the underlying organizational dynamics. In particular, it is of interest in understanding changes in attributes such as…

Insider threat detection has been a challenging task over decades, existing approaches generally employ the traditional generative unsupervised learning methods to produce normal user behavior model and detect significant deviations as…

Group Emotion Recognition (GER) aims to infer collective affect in social environments such as classrooms, crowds, and public events. Many existing approaches rely on explicit individual-level processing, including cropped faces, person…

Established recurrent neural networks are well-suited to solve a wide variety of prediction tasks involving discrete sequences. However, they do not perform as well in the task of dynamical system identification, when dealing with…

Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e.g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states). However, the…

Vision-language models (VLMs) have revolutionized multimodal AI applications but introduce novel security vulnerabilities that remain largely unexplored. We present the first comprehensive study of steganographic prompt injection attacks…

Multi-timescale sequence modeling relies on capturing both local fast dynamics and global slow context; yet, maintaining these capabilities under the strict memory constraints common to edge devices remains an open challenge. Current…

Insider threats continue to present a major challenge for the information security community. Despite constant research taking place in this area; a substantial gap still exists between the requirements of this community and the solutions…

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…