Hidden LLM Backdoors Could Detonate At Massive Scale

AI language models can be secretly trained to steal credentials when triggered by a specific phrase. Here's what the research shows, why safety training can't stop it, and where the $414M AI security ...
IEEE

Deep Learning for Video Anomaly Detection: A Review

Abstract: Video anomaly detection (VAD) aims to discover behaviors or events deviating from the normality in videos. As a long-standing task in the field of computer vision, VAD has witnessed much ...
IEEE

Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models

Abstract: Zero-Shot Anomaly Detection (ZSAD) is an emerging AD paradigm. Unlike the traditional unsupervised AD setting that requires a large number of normal samples to train a model, ZSAD is more ...