Inside the Dataset Powering the Next Generation of AI Text Detection
10 Feb 2026
A new AI model uses benchmark datasets to detect exactly where machine-written text begins, outperforming popular AI detectors.
A New Model That Actually Works: Why Today’s AI Detectors Fail
10 Feb 2026
A new AI model detects exactly where machine writing begins inside human text, outperforming popular AI detectors across domains.
Inside the Model That Outsmarts Popular AI Detection Tools
10 Feb 2026
A new model detects AI-written words inside human text, outperforming popular AI detectors across domains and generators.
This AI Can Spot Exactly Which Words Were Written by ChatGPT
10 Feb 2026
Detect AI-written words inside human text. This research reveals a model that finds AI-generated sections with higher accuracy.
Future of AD Security: Addressing Limitations and Ethical Concerns in Typographic Attack Research
1 Oct 2025
This paper summarizes a comprehensive framework for typographic attacks, proving their effectiveness and transferability against Vision-LLMs like LLaVA
Empirical Study: Evaluating Typographic Attack Effectiveness Against Vision-LLMs in AD Systems
1 Oct 2025
This article presents an empirical study on the effectiveness and transferability of typographic attacks against major Vision-LLMs using AD-specific datasets.
Foreground vs. Background: Analyzing Typographic Attack Placement in Autonomous Driving Systems
1 Oct 2025
This article explores the physical realization of typographic attacks, categorizing their deployment into background and foreground elements
Exploiting Vision-LLM Vulnerability: Enhancing Typographic Attacks with Instructional Directives
30 Sept 2025
This article proposes a linguistic augmentation scheme for typographic attacks using explicit instructional directives.
Methodology for Adversarial Attack Generation: Using Directives to Mislead Vision-LLMs
30 Sept 2025
This article details the multi-step typographic attack pipeline, including Attack Auto-Generation and Attack Augmentation.