Keeley is a PhD student at MIT with a focus on network dynamics and machine learning.
Detection of Coordination Between State-Linked Actors - Paper
We use a discrete-time stochastic model to analyze coordinated activity in an online social network, representing the behaviors of accounts as interacting Markov chains. From a Twitter dataset, we evaluate the coordination, measured by the apparent influence, between pairs of state-linked compared to unaffiliated accounts.
Disambiguating Disinformation: Extending Beyond the Veracity of Online Content - Paper
We present a definition for disinformation - a set or sequence of orchestrated, agenda-driven information actions with the intent to deceive - that is useful in contextualizing disinformation campaigns. And, we expand on our ongoing work to operationalize this definition and demonstrate how detecting disinformation must extend beyond assessing the credibility of a specific publisher, user, or story.
Zero Botnets: An Observe-Pursue-Counter Approach - Paper
Adversarial Internet robots (botnets) represent a growing threat to the safe use and stability of the Internet. Botnets can play a role in launching adversary reconnaissance (scanning and phishing), influence operations (upvoting), and financing operations (ransomware, market manipulation, denial of service, spamming, and ad-click fraud) while obfuscating tailored tactical operations. We analyze defeating botnets using an observe-pursue-counter architecture and evaluate the technical feasibility.
influence - Code
Python implementation of the influence model, a type of networked, discrete-time stochastic model.