Goto

Collaborating Authors

Naval Research Laboratory


Steganographic Internet of Things: Graph Topology Timing Channels

AAAI Conferences

Given the self-aware, artificially intelligent, and complex system-of-systems nature of the Internet of Things (IoT), unintended behavior will manifest itself in many forms. In this paper, we illustrate a method for steganographic messaging that can exploit IoT side channels and be resilient to the heterogeneous communications and application protocols that exist in the IoT. We show that IoT side channels are susceptible to network steganography. Moreover, it is possible to create a data-in-motion steganographic method without network protocol modifications and mathematically bound the channel capacity. Code 5580 Information Management & Decision Architectures Branch US Naval Research Laboratory ira.moskowitz@nrl.navy.mil


Towards Explainable NPCs: A Relational Exploration Learning Agent

AAAI Conferences

Non-player characters (NPCs) in video games are a common form of frustration for players because they generally provide no explanations for their actions or provide simplistic explanations using fixed scripts. Motivated by this, we consider a new design for agents that can learn about their environments, accomplish a range of goals, and explain what they are doing to a supervisor. We propose a framework for studying this type of agent, and compare it to existing reinforcement learning and self-motivated agent frameworks. We propose a novel design for an initial agent that acts within this framework. Finally, we describe an evaluation centered around the supervisor's satisfaction and understanding of the agent's behavior.


Moskowitz

AAAI Conferences

Given the self-aware, artificially intelligent, and complex system-of-systems nature of the Internet of Things (IoT), unintended behavior will manifest itself in many forms. In this paper, we illustrate a method for steganographic messaging that can exploit IoT side channels and be resilient to the heterogeneous communications and application protocols that exist in the IoT. We show that IoT side channels are susceptible to network steganography. Moreover, it is possible to create a data-in-motion steganographic method without network protocol modifications and mathematically bound the channel capacity.


Molineaux

AAAI Conferences

Non-player characters (NPCs) in video games are a common form of frustration for players because they generally provide no explanations for their actions or provide simplistic explanations using fixed scripts. Motivated by this, we consider a new design for agents that can learn about their environments, accomplish a range of goals, and explain what they are doing to a supervisor. We propose a framework for studying this type of agent, and compare it to existing reinforcement learning and self-motivated agent frameworks. We propose a novel design for an initial agent that acts within this framework. Finally, we describe an evaluation centered around the supervisor's satisfaction and understanding of the agent's behavior.


Valuable Information and the Internet of Things

AAAI Conferences

We investigate a theory for Value of Information (VoI) with respect to the Internet of Things (IoT) and IoT’s intrinsic Artificial Intelligence (AI). In an environment of ubiquitous computing and information, information’s value takes on a new dimension. Moreover, when the system in which such a volume of information exists is itself intelligent, the ability to elicit value, in context, will be more complicated. Classi- cal economic theory describes the relationship between value and volume which, though moderated by demand, is highly correlated. In an environment where information is plentiful such as the IoT, the intrinsic intelligence in the system will be a dominant moderator of demand (e.g. self-adapting, self- operating, and self-protecting; controlling access). We exam- ine Howard’s (1966) VoI theory from this perspective and il- lustrate mathematically that Howard’s focus on maximizing value obfuscates another important dimension, the guarantee of value.


Fouad

AAAI Conferences

In our talk we discuss Meta-agents frameworks for working within the Internet of Things (IoT) systems. In particular we discuss our own Meta-agent system called SENtry Agents (SAGE). We discuss why such systems must follow Simon's laws of the Artificial, and because of that must be Holonic.


Meta-Agents: Managing Dynamism in the Internet of Things (IoT) with Multi-agent Networks

AAAI Conferences

In our talk we discuss Meta-agents frameworks for working within the Internet of Things (IoT) systems. In particular we discuss our own Meta-agent system called SENtry Agents (SAGE). We discuss why such systems must follow Simon’s laws of the Artificial, and because of that must be Holonic.



Two Problems Afflicting the Search for a Standard Model of the Mind

AAAI Conferences

We describe two serious problems afflicting the search for astandard model of the mind (SMM), as carried out and prescribedby Laird, Lebiere, and Rosenbloom (LLR). The first problem concerns a glaring omission from SMM, while the second calls into question the evidentiary standards for convergence that motivates the entire SMM agenda. It may well be that neither problem is insuperable, even in the short term. On the other hand, both problems currently stand in theway of making any present pronouncements to the effect that a standard model (or substantive portion thereof) exists and can be used as a benchmark against which other researchers might compare their approaches. The pair of problems is offered in a spirit of collaboration, and in the hope that grappling with them will help move the search a bit closer to the sort of undisputed rigor and predictive power afforded by such models in physics. Our order of business in the sequel is straightforward: we present and briefly discuss each of the two problems in turn, and wrap up with some remarks regarding whether or not these problems can be surmounted, and if so, how.


Dasgupta

AAAI Conferences

In this position paper, we propose a game theoretic formulation of the adversarial learning problem called a RepeatedBayesian Stackelberg Game (RBSG) that can be used by aprediction mechanism to make itself robust against adversarial examples.