Search Results for author: David Noever

Found 48 papers, 2 papers with code

Exploiting Alpha Transparency In Language And Vision-Based AI Systems

no code implementations15 Feb 2024 David Noever, Forrest McKee

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.

Autonomous Driving

PICS: Pipeline for Image Captioning and Search

no code implementations1 Feb 2024 Grant Rosario, David Noever

The growing volume of digital images necessitates advanced systems for efficient categorization and retrieval, presenting a significant challenge in database management and information retrieval.

Asset Management Image Captioning +4

Transparency Attacks: How Imperceptible Image Layers Can Fool AI Perception

no code implementations29 Jan 2024 Forrest McKee, David Noever

A notable attack limitation stems from its dependency on the background (hidden) layer in grayscale as a rough match to the transparent foreground image that the human eye perceives.

Satellite Captioning: Large Language Models to Augment Labeling

no code implementations18 Dec 2023 Grant Rosario, David Noever

With the growing capabilities of modern object detection networks and datasets to train them, it has gotten more straightforward and, importantly, less laborious to get up and running with a model that is quite adept at detecting any number of various objects.

object-detection Object Detection

Evaluating AI Vocational Skills Through Professional Testing

no code implementations17 Dec 2023 David Noever, Matt Ciolino

GPT-3, even without any fine-tuning or exam preparation, managed to achieve a passing score (over 70% correct) on 39% of the professional certifications.

Acoustic Cybersecurity: Exploiting Voice-Activated Systems

no code implementations23 Nov 2023 Forrest McKee, David Noever

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.

Visual AI and Linguistic Intelligence Through Steerability and Composability

no code implementations18 Nov 2023 David Noever, Samantha Elizabeth Miller Noever

This study explores the capabilities of multimodal large language models (LLMs) in handling challenging multistep tasks that integrate language and vision, focusing on model steerability, composability, and the application of long-term memory and context understanding.

Can Large Language Models Find And Fix Vulnerable Software?

no code implementations20 Aug 2023 David Noever

In this study, we evaluated the capability of Large Language Models (LLMs), particularly OpenAI's GPT-4, in detecting software vulnerabilities, comparing their performance against traditional static code analyzers like Snyk and Fortify.

Multimodal Analysis Of Google Bard And GPT-Vision: Experiments In Visual Reasoning

no code implementations17 Aug 2023 David Noever, Samantha Elizabeth Miller Noever

Addressing the gap in understanding visual comprehension in Large Language Models (LLMs), we designed a challenge-response study, subjecting Google Bard and GPT-Vision to 64 visual tasks, spanning categories like "Visual Situational Reasoning" and "Next Scene Prediction."

Common Sense Reasoning Optical Character Recognition +1

AI Text-to-Behavior: A Study In Steerability

no code implementations7 Aug 2023 David Noever, Sam Hyams

The research explores the steerability of Large Language Models (LLMs), particularly OpenAI's ChatGPT iterations.

Professional Certification Benchmark Dataset: The First 500 Jobs For Large Language Models

no code implementations7 May 2023 David Noever, Matt Ciolino

It compares the performance of two AI models, GPT-3 and Turbo-GPT3. 5, on a benchmark dataset of 1149 professional certifications, emphasizing vocational readiness rather than academic performance.

NUANCE: Near Ultrasound Attack On Networked Communication Environments

no code implementations25 Apr 2023 Forrest McKee, David Noever

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.

Grading Conversational Responses Of Chatbots

no code implementations1 Feb 2023 Grant Rosario, David Noever

Chatbots have long been capable of answering basic questions and even responding to obscure prompts, but recently their improvements have been far more significant.

Machine Translation Translation

Numeracy from Literacy: Data Science as an Emergent Skill from Large Language Models

no code implementations31 Jan 2023 David Noever, Forrest McKee

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.

Descriptive Feature Importance +2

Chatbots in a Honeypot World

no code implementations10 Jan 2023 Forrest McKee, David Noever

The paper illustrates ten diverse tasks that a conversational agent or large language model might answer appropriately to the effects of command-line attacker.

Language Modelling Large Language Model

Chatbots As Fluent Polyglots: Revisiting Breakthrough Code Snippets

no code implementations5 Jan 2023 David Noever, Kevin Williams

The research applies AI-driven code assistants to analyze a selection of influential computer code that has shaped modern technology, including email, internet browsing, robotics, and malicious software.

Chatbots as Problem Solvers: Playing Twenty Questions with Role Reversals

no code implementations1 Jan 2023 David Noever, Forrest McKee

The research introduces four novel cases where the chatbot fields the questions, asks the questions, both question-answer roles, and finally tries to guess appropriate contextual emotions.

Chatbot

Chatbots in a Botnet World

no code implementations18 Dec 2022 Forrest McKee, David Noever

Question-and-answer formats provide a novel experimental platform for investigating cybersecurity questions.

The Turing Deception

no code implementations9 Dec 2022 David Noever, Matt Ciolino

This research revisits the classic Turing test and compares recent large language models such as ChatGPT for their abilities to reproduce human-level comprehension and compelling text generation.

Question Answering Text Generation

Soft Labels for Rapid Satellite Object Detection

no code implementations1 Dec 2022 Matthew Ciolino, Grant Rosario, David Noever

We show that soft labels can be used to train a model that is almost as accurate as a model trained on the original data.

Image Classification Object +2

Soft-labeling Strategies for Rapid Sub-Typing

no code implementations23 Sep 2022 Grant Rosario, David Noever, Matt Ciolino

The challenge of labeling large example datasets for computer vision continues to limit the availability and scope of image repositories.

object-detection Object Detection

Physical Systems Modeled Without Physical Laws

1 code implementation26 Jul 2022 David Noever, Samuel Hyams

Physics-based simulations typically operate with a combination of complex differentiable equations and many scientific and geometric inputs.

Word Play for Playing Othello (Reverses)

no code implementations18 Jul 2022 Samantha E. Miller Noever, David Noever

Like previous work with chess and Go, these language models offer a novel way to generate plausible game archives, particularly for comparing opening moves across a larger sample than humanly possible to explore.

Language Modelling

Color Teams for Machine Learning Development

no code implementations20 Oct 2021 Josh Kalin, David Noever, Matthew Ciolino

Machine learning and software development share processes and methodologies for reliably delivering products to customers.

BIG-bench Machine Learning

POSSE: Patterns of Systems During Software Encryption

no code implementations24 Sep 2021 David Noever, Samantha Miller Noever

This research recasts ransomware detection using performance monitoring and statistical machine learning.

BIG-bench Machine Learning regression

Puzzle Solving without Search or Human Knowledge: An Unnatural Language Approach

no code implementations7 Sep 2021 David Noever, Ryerson Burdick

The application of Generative Pre-trained Transformer (GPT-2) to learn text-archived game notation provides a model environment for exploring sparse reward gameplay.

Rubik's Cube

Overhead-MNIST: Machine Learning Baselines for Image Classification

no code implementations1 Jul 2021 Erik Larsen, David Noever, Korey MacVittie, John Lilly

Twenty-three machine learning algorithms were trained then scored to establish baseline comparison metrics and to select an image classification algorithm worthy of embedding into mission-critical satellite imaging systems.

BIG-bench Machine Learning Classification +1

Rock Hunting With Martian Machine Vision

no code implementations9 Apr 2021 David Noever, Samantha E. Miller Noever

The Mars Perseverance rover applies computer vision for navigation and hazard avoidance.

Object Recognition

Virus-MNIST: A Benchmark Malware Dataset

no code implementations28 Feb 2021 David Noever, Samantha E. Miller Noever

As a benchmark using deep learning methods (MobileNetV2), we find an overall 80% accuracy for virus identification by families when beneware is included.

Clustering Image Classification +1

Overhead MNIST: A Benchmark Satellite Dataset

no code implementations8 Feb 2021 David Noever, Samantha E. Miller Noever

The research presents an overhead view of 10 important objects and follows the general formatting requirements of the most popular machine learning task: digit recognition with MNIST.

Management Object Recognition +1

Local Translation Services for Neglected Languages

no code implementations5 Jan 2021 David Noever, Josh Kalin, Matt Ciolino, Dom Hambrick, Gerry Dozier

Taking advantage of computationally lightweight, but high-quality translators prompt consideration of new applications that address neglected languages.

Sentence Translation

Black Box to White Box: Discover Model Characteristics Based on Strategic Probing

no code implementations7 Sep 2020 Josh Kalin, Matthew Ciolino, David Noever, Gerry Dozier

With the process in this paper, a structured set of input probes and the output of the model become the training data for a deep classifier.

BIG-bench Machine Learning Image Classification +1

The Chess Transformer: Mastering Play using Generative Language Models

2 code implementations2 Aug 2020 David Noever, Matt Ciolino, Josh Kalin

This work demonstrates that natural language transformers can support more generic strategic modeling, particularly for text-archived games.

The Go Transformer: Natural Language Modeling for Game Play

no code implementations7 Jul 2020 Matthew Ciolino, David Noever, Josh Kalin

This work applies natural language modeling to generate plausible strategic moves in the ancient game of Go.

Game of Go Language Modelling +2

Systematic Attack Surface Reduction For Deployed Sentiment Analysis Models

no code implementations19 Jun 2020 Josh Kalin, David Noever, Gerry Dozier

This work proposes a structured approach to baselining a model, identifying attack vectors, and securing the machine learning models after deployment.

BIG-bench Machine Learning Sentiment Analysis

The Enron Corpus: Where the Email Bodies are Buried?

no code implementations24 Jan 2020 David Noever

To probe the largest public-domain email database for indicators of fraud, we apply machine learning and accomplish four investigative tasks.

Discoverability in Satellite Imagery: A Good Sentence is Worth a Thousand Pictures

no code implementations3 Jan 2020 David Noever, Wes Regian, Matt Ciolino, Josh Kalin, Dom Hambrick, Kaye Blankenship

Small satellite constellations provide daily global coverage of the earth's landmass, but image enrichment relies on automating key tasks like change detection or feature searches.

Change Detection Descriptive +4

Training Set Effect on Super Resolution for Automated Target Recognition

no code implementations29 Oct 2019 Matthew Ciolino, David Noever, Josh Kalin

This suggests a possible improvement to automated target recognition in image classification and object detection.

Binary Classification General Classification +6

Classifier Suites for Insider Threat Detection

no code implementations30 Jan 2019 David Noever

We address the relative rarity of threats as a case of low signal-to-noise (< 0. 02% malicious to benign activities), and then train on both under-sampled and over-sampled data which is statistically balanced to identify nefarious actors.

Data Strategies for Fleetwide Predictive Maintenance

no code implementations11 Dec 2018 David Noever

For predictive maintenance, we examine one of the largest public datasets for machine failures derived along with their corresponding precursors as error rates, historical part replacements, and sensor inputs.

Feature Importance regression

Machine Learning Suites for Online Toxicity Detection

no code implementations3 Oct 2018 David Noever

To identify and classify toxic online commentary, the modern tools of data science transform raw text into key features from which either thresholding or learning algorithms can make predictions for monitoring offensive conversations.

BIG-bench Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.