HarassGuard: Detecting Harassment Behaviors in Social Virtual Reality with Vision-Language Models

Sexual harassment represents a pervasive societal challenge, with a substantial proportion of incidents remaining unreported due to insufficient evidence and delayed intervention mechanisms. Smart surveillance systems capable of detecting such incidents in real-time could assist law enforcement and serve as a deterrent. However, video-based harassment detection poses significant challenges, including variations in clothing, illumina- tion, partial occlusions, low resolution, and diverse camera view- points. Despite its social importance, this problem has received limited research attention, primarily due to the scarcity of large- scale annotated video datasets. To address this gap, we extend the Sexual Harassment Video (SHV) dataset to 600 short video clips sourced from YouTube and annotated into harassment and non-harassment categories using consistent labeling guidelines. We fine-tune three state-of-the-art video transformer models, VideoMAE, ViViT, and TimeSformer, pretrained on Kinetics- 400, for binary harassment classification. Experimental results show that all three models achieve competitive classification performance, with TimeSformer attaining the highest test accu- racy of 92.27%, outperforming VideoMAE 91.71% and ViViT 91.16% on the extended SHV test set. Our analysis reveals that performance is notably influenced by dataset size, video quality, frame sampling strategy, and model architecture. This work presents a comprehensive evaluation of modern video transformers for this sensitive real-world task.

Augmented reality (AR) has rapidly expanded over the past decade. As AR becomes increasingly integrated into daily life, its security and reliability emerge as critical challenges. Among various threats, contradictory virtual content attacks, where malicious or inconsistent virtual elements are introduced into the user's view, pose a unique risk by misleading users, creating semantic confusion, or delivering harmful information. In this work, we systematically model such attacks and present ContrAR, a novel benchmark for evaluating the robustness of vision-language models (VLMs) against virtual content manipulation and contradiction in AR. ContrAR contains 312 real-world AR videos validated by 10 human participants. We further benchmark 11 VLMs, including both commercial and open-source models. Experimental results reveal that while current VLMs exhibit reasonable understanding of contradictory virtual content, room still remains for improvement in detecting and reasoning about adversarial content manipulations in AR environments. Moreover, balancing detection accuracy and latency remains challenging.

As video generation paradigms evolve from localized manipulation to full-scene synthesis, AI-generated video detection becomes increasingly challenging, as forgeries exhibit coherent global structure and high perceptual realism. However, existing benchmarks are biased toward perceptual fidelity and primarily evaluate detectors based on perceptual artifacts, providing limited coverage of scenarios that require reasoning about violations of physical laws, structural coherence, or social logic. This dataset bias shapes current approaches and results in a Perception-Reasoning Gap: artifact-centric models capture low-level statistical irregularities yet lack semantic inference, whereas vision-language models perform semantic reasoning but remain insensitive to fine-grained forensic cues. To bridge this gap, we propose SafeGuard, a multi-agent framework that enables collaborative specialization between forensic perception and semantic reasoning. A hierarchical perceptual solver extracts fine-grained forensic evidence, while a self-reflective verifier enforces consistency between semantic inference and physical plausibility, forming an interpretable evidence chain. To support evaluation, we introduce SafeVid, a novel AI-generated video detection benchmark comprising 20K videos spanning 10 social risk categories, designed to evaluate physical plausibility, structural consistency, and the rationality of social behaviors. Extensive experiments demonstrate the generalization of SafeGuard, improving accuracy on SafeVid by +18.7% and consistently outperforming prior methods across four public benchmarks.