20 citations · 25 across the 11 of their papers we have counts for
13 papers
SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems
Rui Yang, Junjie Xu, Zhengyu Liu +4
Safe agents can fail together. Multi-agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating failures that local checks may…
Comment and Control: Hijacking Agentic Workflows via Context-Grounded Evolution
Neil Fendley, Zhengyu Liu, Aonan Guan +2
Automation platforms such as GitHub Actions and n8n are increasingly adopting so-called agentic workflows, which integrate Large Language Model (LLM) agents for tasks such as code…
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…
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…
Mirror Mirror on the Wall, Have I Forgotten it All? A New Framework for Evaluating Machine Unlearning
Brennon Brimhall, Philip Mathew, Neil Fendley +2
Machine unlearning methods take a model trained on a dataset and a forget set, then attempt to produce a model as if it had only been trained on the examples not in the forget set.…
Continual Reinforcement Learning with TELLA
Neil Fendley, Cash Costello, Eric Nguyen +2
Training reinforcement learning agents that continually learn across multiple environments is a challenging problem. This is made more difficult by a lack of reproducible experimen…
L2Explorer: A Lifelong Reinforcement Learning Assessment Environment
Erik C. Johnson, Eric Q. Nguyen, Blake Schreurs +6
Despite groundbreaking progress in reinforcement learning for robotics, gameplay, and other complex domains, major challenges remain in applying reinforcement learning to the evolv…
Addressing Visual Search in Open and Closed Set Settings
Nathan Drenkow, Philippe Burlina, Neil Fendley +2
Searching for small objects in large images is a task that is both challenging for current deep learning systems and important in numerous real-world applications, such as remote s…
Attack Agnostic Detection of Adversarial Examples via Random Subspace Analysis
Nathan Drenkow, Neil Fendley, Philippe Burlina
Whilst adversarial attack detection has received considerable attention, it remains a fundamentally challenging problem from two perspectives. First, while threat models can be wel…
Jacks of All Trades, Masters Of None: Addressing Distributional Shift and Obtrusiveness via Transparent Patch Attacks
Neil Fendley, Max Lennon, I-Jeng Wang +2
We focus on the development of effective adversarial patch attacks and -- for the first time -- jointly address the antagonistic objectives of attack success and obtrusiveness via…
The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models
Kiran Karra, Chace Ashcraft, Neil Fendley
In this paper, we introduce the TrojAI software framework, an open source set of Python tools capable of generating triggered (poisoned) datasets and associated deep learning (DL)…
Adversarial Examples in Remote Sensing
Wojciech Czaja, Neil Fendley, Michael Pekala +2
This paper considers attacks against machine learning algorithms used in remote sensing applications, a domain that presents a suite of challenges that are not fully addressed by c…
Functional Map of the World
Gordon Christie, Neil Fendley, James Wilson +1
We present a new dataset, Functional Map of the World (fMoW), which aims to inspire the development of machine learning models capable of predicting the functional purpose of build…