Detection of Hate and Threat in Digital Forensics: A Case-Driven Multimodal Approach

TL;DR

This paper introduces a multimodal forensic framework that detects hate and threats by analyzing heterogeneous evidence like images and text, improving interpretability and evidentiary traceability.

Contribution

It presents a case-driven approach that explicitly identifies evidence types and applies modality-specific analysis, enhancing forensic decision-making and evidence interpretation.

Findings

Consistent detection performance across heterogeneous evidence scenarios

Improved interpretability and traceability in forensic analysis

Effective use of vision-language models for semantic reasoning

Abstract

Digital forensic investigations increasingly rely on heterogeneous evidence such as images, scanned documents, and contextual reports. These artifacts may contain explicit or implicit expressions of harm, hate, threat, violence, or intimidation, yet existing automated approaches often assume clean text input or apply vision models without forensic justification. This paper presents a case-driven multimodal approach for hate and threat detection in forensic analysis. The proposed framework explicitly determines the presence and source of textual evidence, distinguishing between embedded text, associated contextual text, and image-only evidence. Based on the identified evidence configuration, the framework selectively applies text analysis, multimodal fusion, or image-only semantic reasoning using vision language models with vision transformer backbones (ViT). By conditioning inference on evidence availability, the approach mirrors forensic decision-making, improves evidentiary traceability, and avoids unjustified modality assumptions. Experimental evaluation on forensic-style image evidence demonstrates consistent and interpretable behavior across heterogeneous evidence scenarios.