activity
20242026
most citedHumanity's Last Exam

18 citations · 18 across the 2 of their papers we have counts for

collaborators
Showing cs.CRShow all

6 papers · 1 filter

cs.CR2026

Rendering on Real Silicon: GPU Render-Timing as a Passive, AI-Resistant CAPTCHA Signal

David Noever, Forrest McKee

Conventional CAPTCHAs pose puzzles that modern AI systems increasingly solve, while behavioral and cryptographic-attestation defenses carry privacy or enrollment costs. We investig…

cs.CR2025

Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills

David Noever

This paper identifies and analyzes a novel vulnerability class in Model Context Protocol (MCP) based agent systems. The attack chain describes and demonstrates how benign, individu…

cs.CR2025

Favicon Trojans: Executable Steganography Via Ico Alpha Channel Exploitation

David Noever, Forrest McKee

This paper presents a novel method of executable steganography using the alpha transparency layer of ICO image files to embed and deliver self-decompressing JavaScript payloads wit…

cs.CR2025

Infecting Generative AI With Viruses

David Noever, Forrest McKee

This study demonstrates a novel approach to testing the security boundaries of Vision-Large Language Model (VLM/ LLM) using the EICAR test file embedded within JPEG images. We succ…

cs.CR2024

Language Models And A Second Opinion Use Case: The Pocket Professional

David Noever

This research tests the role of Large Language Models (LLMs) as formal second opinion tools in professional decision-making, particularly focusing on complex medical cases where ev…

cs.CR2024

Hallucinating AI Hijacking Attack: Large Language Models and Malicious Code Recommenders

David Noever, Forrest McKee

The research builds and evaluates the adversarial potential to introduce copied code or hallucinated AI recommendations for malicious code in popular code repositories. While found…