Zobrazeno 1 - 10
of 17
pro vyhledávání: '"McKee, Forrest"'
Autor:
Noever, David, McKee, Forrest
This research introduces a novel evaluation framework designed to assess large language models' (LLMs) ability to acknowledge uncertainty on 675 fundamentally unsolvable problems. Using a curated dataset of graduate-level grand challenge questions wi
Externí odkaz:
http://arxiv.org/abs/2411.14486
Autor:
Noever, David, McKee, Forrest
The research builds and evaluates the adversarial potential to introduce copied code or hallucinated AI recommendations for malicious code in popular code repositories. While foundational large language models (LLMs) from OpenAI, Google, and Anthropi
Externí odkaz:
http://arxiv.org/abs/2410.06462
Autor:
McKee, Forrest, Noever, David
The widespread adoption of voice-activated systems has modified routine human-machine interaction but has also introduced new vulnerabilities. This paper investigates the susceptibility of automatic speech recognition (ASR) algorithms in these system
Externí odkaz:
http://arxiv.org/abs/2404.04769
Autor:
Noever, David, McKee, Forrest
This investigation reveals a novel exploit derived from PNG image file formats, specifically their alpha transparency layer, and its potential to fool multiple AI vision systems. Our method uses this alpha layer as a clandestine channel invisible to
Externí odkaz:
http://arxiv.org/abs/2402.09671
Autor:
McKee, Forrest, Noever, David
This paper investigates a novel algorithmic vulnerability when imperceptible image layers confound multiple vision models into arbitrary label assignments and captions. We explore image preprocessing methods to introduce stealth transparency, which t
Externí odkaz:
http://arxiv.org/abs/2401.15817
Autor:
McKee, Forrest, Noever, David
In this study, we investigate the emerging threat of inaudible acoustic attacks targeting digital voice assistants, a critical concern given their projected prevalence to exceed the global population by 2024. Our research extends the feasibility of t
Externí odkaz:
http://arxiv.org/abs/2312.00039
Autor:
McKee, Forrest, Noever, David
The paper applies reinforcement learning to novel Internet of Thing configurations. Our analysis of inaudible attacks on voice-activated devices confirms the alarming risk factor of 7.6 out of 10, underlining significant security vulnerabilities scor
Externí odkaz:
http://arxiv.org/abs/2307.12204
Autor:
McKee, Forrest, Noever, David
This study investigates a primary inaudible attack vector on Amazon Alexa voice services using near ultrasound trojans and focuses on characterizing the attack surface and examining the practical implications of issuing inaudible voice commands. The
Externí odkaz:
http://arxiv.org/abs/2305.10358
Autor:
Noever, David, McKee, Forrest
Large language models (LLM) such as OpenAI's ChatGPT and GPT-3 offer unique testbeds for exploring the translation challenges of turning literacy into numeracy. Previous publicly-available transformer models from eighteen months prior and 1000 times
Externí odkaz:
http://arxiv.org/abs/2301.13382
Autor:
McKee, Forrest, Noever, David
Question-and-answer agents like ChatGPT offer a novel tool for use as a potential honeypot interface in cyber security. By imitating Linux, Mac, and Windows terminal commands and providing an interface for TeamViewer, nmap, and ping, it is possible t
Externí odkaz:
http://arxiv.org/abs/2301.03771