Search Results for author:
Found 9 papers, 0 papers with code
Exploiting Alpha Transparency In Language And Vision-Based AI Systems
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.
Transparency Attacks: How Imperceptible Image Layers Can Fool AI Perception
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.
Acoustic Cybersecurity: Exploiting Voice-Activated Systems
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.
Adversarial Agents For Attacking Inaudible Voice Activated Devices
The paper applies reinforcement learning to novel Internet of Thing configurations.
NUANCE: Near Ultrasound Attack On Networked Communication Environments
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.
Numeracy from Literacy: Data Science as an Emergent Skill from Large Language Models
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.
Chatbots in a Honeypot World
The paper illustrates ten diverse tasks that a conversational agent or large language model might answer appropriately to the effects of command-line attacker.
Chatbots as Problem Solvers: Playing Twenty Questions with Role Reversals
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.
Chatbots in a Botnet World
Question-and-answer formats provide a novel experimental platform for investigating cybersecurity questions.
