Cybersecurity defense is inherently adversarial, making multi‑agent reinforcement learning a natural fit, but simultaneous training of competing agents in complex environments is notoriously unstable. This work proposes a game‑theoretic deep RL framework for CybORG that extends Nash Q‑learning with a centralized joint Q‑network (critic) and separate decentralized policies. The critic …

This project focuses on decoding neural signals from brain areas involved in speech production (ventral premotor cortex and Broca's area) into text by combining brain feature extractors and ASR architectures. Whereas previous research disregards the semantic regions (e.g. Area 44), this project explores combining semantic and motor (articulatory) signals in …

This project develops a reconstruction-based anomaly detection system for network intrusions, utilizing autoencoders with attention mechanism to identify intrusions by analyzing the loss in reconstructing network traffic data. This approach works better than classical classifiers, which need to be trained on every possible attack type, and fail to detect novel …

Large Language Model (LLM) agents are increasingly studied in multi-turn, multi-agent scenarios, yet most existing setups emphasize open-ended role-play rather than controlled evaluation. AsymPuzl provides a minimal but expressive two-agent puzzle environment designed to isolate communication under information asymmetry. Each agent observes complementary but incomplete views of a symbolic puzzle …

Cyber defense operations increasingly require long-term strategic planning under uncertainty and resource constraints. We can use combinatorial auctions for allocating defensive action bundles in a realistic cyber environment, using host-specific valuations derived from reinforcement learning (RL) Q-values. These Q-values encode long-term expected utility, allowing upstream planning. Publication (IEEE HPEC) Image …

Deep Neural Networks (DNNs) can have very high performance in a visual recognition task but are prone to noise and adversarial attacks. One main problem of training a DNN is the input often lay in very high dimensional space which leads to a high number of parameters to train. This …

Current neural network models that deal with data on the spectral plane (magnitude and phase) only take as input the magnitude, and do not incorporate, in a meaningful way, the phase information. Research has shown that the output of biological neurons is affected by the phase of its inputs. In …

Neural networks are an immensely powerful tool for many difficult problems, but often require computational power beyond that of small devices such as embedded systems, Internet of Things devices, and mobile phones. In this project we aim to create computationally efficient neural networks, networks with smaller memory and compute footprints …

The “intrinsic” dimensionality of a dataset is a quantity of great interest in the machine learning community. There are many techniques aimed at estimating this “intrinsic” dimensionality, but there are currently none which have demonstrated scalability to large, complex datasets. In this project we aim to find the intrinsic dimension …

With the emergence of social media, information and influence propagation in online networks has become an active field of research over the last decade. Individuals often participate in multiple social networks which leads to information spreading faster and the propagation becoming more complex. We would like to understand the pattern …

A popular theory of intelligence argues that intelligence arises from the connections between primitive computing units rather than the computing units themselves. Interestingly, neurons in the brain form topological structures for processing different types of information. We are exploring the relationship between graph topology and model performance using Graph Neural …

Reinforcement learning has shown much success in games such as chess, backgammon and Go. However, in most of these games, agents have full knowledge of the environment at all times. We describe a deep learning model that successfully maximizes its score using reinforcement learning in a game with incomplete and …

The problem of referring expression is a more domain specific area of image captioning with the goal of describing a sub-region of a given image. Rational Speech Act (RSA) framework is a probabilistic reasoning approach that can generate sentences based on game theory systems of speaker – listener. The advantage …

Baseball is a well known, repeated, finite, adversarial, stochastic game that has a massive amount of available data. On the other hand, Reinforcement Learning (RL) models take significant time and resources to train. By fusing Game Theory and RL, we are answering interesting questions such as “given a video of …

Side channel analysis involves using externally recorded signals from a device (such as electromagnetic radiation or power consumption) to determine what the device is preforming. Our current work involves using this avenue of data in conjunction with machine learning techniques to accomplish two tasks. First is anomaly detection, in which …