5 papers
Trojans in Artificial Intelligence (TrojAI) Final Report
Kristopher W. Reese, Taylor Kulp-McDowall, Michael Majurski +68
The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI T…
Backdoors in DRL: Four Environments Focusing on In-distribution Triggers
Chace Ashcraft, Ted Staley, Josh Carney +4
Backdoor attacks, or trojans, pose a security risk by concealing undesirable behavior in deep neural network models. Open-source neural networks are downloaded from the internet da…
A Systematic Review of Poisoning Attacks Against Large Language Models
Neil Fendley, Edward W. Staley, Joshua Carney +3
With the widespread availability of pretrained Large Language Models (LLMs) and their training datasets, concerns about the security risks associated with their usage has increased…
Unconstrained Large-scale 3D Reconstruction and Rendering across Altitudes
Neil Joshi, Joshua Carney, Nathanael Kuo +3
Production of photorealistic, navigable 3D site models requires a large volume of carefully collected images that are often unavailable to first responders for disaster relief or l…
Investigating the Treacherous Turn in Deep Reinforcement Learning
Chace Ashcraft, Kiran Karra, Josh Carney +1
The Treacherous Turn refers to the scenario where an artificial intelligence (AI) agent subtly, and perhaps covertly, learns to perform a behavior that benefits itself but is deeme…