no code implementations • 4 Apr 2024 • Tyler Cody, Bingtong Li, Peter A. Beling
This paper addresses the urgent need for messaging standards in the operational test and evaluation (T&E) of machine learning (ML) applications, particularly in edge ML applications embedded in systems like robots, satellites, and unmanned vehicles.
no code implementations • 4 Apr 2024 • Anli du Preez, Peter A. Beling, Tyler Cody
The framework is formulated in terms of input-output systems and is further divided into system structure and system behavior.
no code implementations • 14 Feb 2024 • Cheng Wang, Christopher Redino, Abdul Rahman, Ryan Clark, Daniel Radke, Tyler Cody, Dhruv Nandakumar, Edward Bowen
Results on a typical network configuration show that the RL agent can automatically discover resilient C2 attack paths utilizing both Tor-based and conventional communication channels, while also bypassing network firewalls.
no code implementations • 13 Jan 2024 • Cheng Wang, Akshay Kakkar, Christopher Redino, Abdul Rahman, Ajinsyam S, Ryan Clark, Daniel Radke, Tyler Cody, Lanxiao Huang, Edward Bowen
Command and control (C2) paths for issuing commands to malware are sometimes the only indicators of its existence within networks.
no code implementations • 28 Dec 2023 • Padmaksha Roy, Tyler Cody, Himanshu Singhal, Kevin Choi, Ming Jin
Domain generalization focuses on leveraging knowledge from multiple related domains with ample training data and labels to enhance inference on unseen in-distribution (IN) and out-of-distribution (OOD) domains.
no code implementations • 16 Nov 2023 • Niloofar Shadab, Tyler Cody, Alejandro Salado, Peter Beling
There is a lack of formalism for some key foundational concepts in systems engineering.
no code implementations • 10 Oct 2023 • Jaganmohan Chandrasekaran, Tyler Cody, Nicola McCarthy, Erin Lanus, Laura Freeman
This report presents best practices for the Test and Evaluation (T&E) of ML-enabled software systems across its lifecycle.
no code implementations • 28 Feb 2023 • Tyler Cody, Laura Freeman
Results show that coverage metrics can correlate with classification error.
no code implementations • 28 Feb 2023 • Sai Prathyush Katragadda, Tyler Cody, Peter Beling, Laura Freeman
The proposed methods are data-centric, as opposed to model-centric, and through our experiments we show that the inclusion of coverage in active learning leads to sampling data that tends to be the best in transferring to better performing models and has a competitive sampling bias compared to benchmark methods.
no code implementations • 6 Nov 2022 • Lanxiao Huang, Tyler Cody, Christopher Redino, Abdul Rahman, Akshay Kakkar, Deepak Kushwaha, Cheng Wang, Ryan Clark, Daniel Radke, Peter Beling, Edward Bowen
Reinforcement learning (RL) operating on attack graphs leveraging cyber terrain principles are used to develop reward and state associated with determination of surveillance detection routes (SDR).
no code implementations • 4 Aug 2022 • Tyler Cody
Transfer learning, multi-task learning, and meta-learning are well-studied topics concerned with the generalization of knowledge across learning tasks and are closely related to general intelligence.
no code implementations • 4 Aug 2022 • Tyler Cody, Niloofar Shadab, Alejandro Salado, Peter Beling
Engineering methods are centered around traditional notions of decomposition and recomposition that rely on partitioning the inputs and outputs of components to allow for component-level properties to hold after their composition.
no code implementations • 28 Jan 2022 • Tyler Cody, Abdul Rahman, Christopher Redino, Lanxiao Huang, Ryan Clark, Akshay Kakkar, Deepak Kushwaha, Paul Park, Peter Beling, Edward Bowen
Reinforcement learning (RL), in conjunction with attack graphs and cyber terrain, are used to develop reward and state associated with determination of optimal paths for exfiltration of data in enterprise networks.
no code implementations • 28 Jan 2022 • Tyler Cody, Erin Lanus, Daniel D. Doyle, Laura Freeman
In contrast to prior work which has focused on the use of coverage in regard to the internal of neural networks, this paper considers coverage over simple features derived from inputs and outputs.
no code implementations • 29 Nov 2021 • Tyler Cody
Herein, Mesarovician abstract systems theory is used as a super-structure for learning.
no code implementations • 20 Aug 2021 • Rohit Gangupantulu, Tyler Cody, Abdul Rahman, Christopher Redino, Ryan Clark, Paul Park
Cyber attacks pose existential threats to nations and enterprises.
no code implementations • 16 Aug 2021 • Rohit Gangupantulu, Tyler Cody, Paul Park, Abdul Rahman, Logan Eisenbeiser, Dan Radke, Ryan Clark
Reinforcement learning (RL) has been applied to attack graphs for penetration testing, however, trained agents do not reflect reality because the attack graphs lack operational nuances typically captured within the intelligence preparation of the battlefield (IPB) that include notions of (cyber) terrain.
no code implementations • 2 Jul 2021 • Tyler Cody, Peter A. Beling
We interpret existing frameworks in terms of ours and go beyond existing frameworks to define notions of transferability, transfer roughness, and transfer distance.
no code implementations • 2 Jul 2021 • Tyler Cody, Stephen Adams, Peter A. Beling
We consider the use of transfer distance in the design of machine rebuild procedures to allow for transferable prognostic models.