16 papers
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…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1144
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
Prompt-to-Parts: Generative AI for Physical Assembly and Scalable Instructions
David Noever
We present a framework for generating physically realizable assembly instructions from natural language descriptions. Unlike unconstrained text-to-3D approaches, our method operate…
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…
Moravec's Paradox: Towards an Auditory Turing Test
David Noever, Forrest McKee
This research work demonstrates that current AI systems fail catastrophically on auditory tasks that humans perform effortlessly. Drawing inspiration from Moravec's paradox (i.e.,…
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…