The network of services, including delivery, farming, and environmental monitoring, has experienced exponential expansion in the past decade with Unmanned Aerial Vehicles (UAVs). Yet, UAVs are not robust enough against cyberattacks, especially on the Controller Area Network (CAN) bus. The CAN bus is a general-purpose vehicle-bus standard to enable microcontrollers and in-vehicle computers to interact, primarily connecting different Electronic Control Units (ECUs). In this study, we focus on solving some of the most critical security weaknesses in UAVs by developing a novel graph-based intrusion detection system (IDS) leveraging the Uncomplicated Application-level Vehicular Communication and Networking (UAVCAN) protocol. First, we decode CAN messages based on UAVCAN protocol specification; second, we present a comprehensive method of transforming tabular UAVCAN messages into graph structures. Lastly, we apply various graph-based machine learning models for detecting cyber-attacks on the CAN bus, including graph convolutional neural networks (GCNNs), graph attention networks (GATs), Graph Sample and Aggregate Networks (GraphSAGE), and graph structure-based transformers. Our findings show that inductive models such as GATs, GraphSAGE, and graph-based transformers can achieve competitive and even better accuracy than transductive models like GCNNs in detecting various types of intrusions, with minimum information on protocol specification, thus providing a generic robust solution for CAN bus security for the UAVs. We also compared our results with baseline single-layer Long Short-Term Memory (LSTM) and found that all our graph-based models perform better without using any decoded features based on the UAVCAN protocol, highlighting higher detection performance with protocol-independent capability.

Threat hunting analyzes large, noisy, high-dimensional data to find sparse adversarial behavior. We believe adversarial activities, however they are disguised, are extremely difficult to completely obscure in high dimensional space. In this paper, we employ these latent features of cyber data to find anomalies via a prototype tool called Cyber Log Embeddings Model (CLEM). CLEM was trained on Zeek network traffic logs from both a real-world production network and an from Internet of Things (IoT) cybersecurity testbed. The model is deliberately overtrained on a sliding window of data to characterize each window closely. We use the Adjusted Rand Index (ARI) to comparing the k-means clustering of CLEM output to expert labeling of the embeddings. Our approach demonstrates that there is promise in using natural language modeling to understand cyber data.

Relation extraction (RE) is the core NLP task of inferring semantic relationships between entities from text. Standard supervised RE techniques entail training modules to tag tokens comprising entity spans and then predict the relationship between them. Recent work has instead treated the problem as a \emph{sequence-to-sequence} task, linearizing relations between entities as target strings to be generated conditioned on the input. Here we push the limits of this approach, using larger language models (GPT-3 and Flan-T5 large) than considered in prior work and evaluating their performance on standard RE tasks under varying levels of supervision. We address issues inherent to evaluating generative approaches to RE by doing human evaluations, in lieu of relying on exact matching. Under this refined evaluation, we find that: (1) Few-shot prompting with GPT-3 achieves near SOTA performance, i.e., roughly equivalent to existing fully supervised models; (2) Flan-T5 is not as capable in the few-shot setting, but supervising and fine-tuning it with Chain-of-Thought (CoT) style explanations (generated via GPT-3) yields SOTA results. We release this model as a new baseline for RE tasks.

COLUMBUS, OHIO – Ohio crews cleaning up a massive former Cold War-era uranium enrichment plant in Ohio plan this summer to deploy a high-tech helper: an autonomous, radiation-measuring robot that will roll through kilometers of large overhead pipes to spot potentially hazardous residual uranium. Officials say it's safer, more accurate and tremendously faster than having workers take external measurements to identify which pipes need to be removed and decontaminated at the Portsmouth Gaseous Diffusion Plant in Piketon. They say it could save taxpayers tens of millions of dollars on cleanups of that site and one near Paducah, Kentucky, which for decades enriched uranium for nuclear reactors and weapons. The RadPiper robot was developed at Carnegie Mellon University in Pittsburgh for the U.S. Department of Energy, which envisions using similar technology at other nuclear complexes such as the Savannah River Site in Aiken, South Carolina, and the Hanford Site in Richland, Washington. Roboticist William "Red" Whittaker, who began his career developing robots to help clean up the Three Mile Island nuclear power accident and now directs Carnegie Mellon's Field Robotics Center, said technology like RadPiper could transform key tasks in cleaning up the country's nuclear legacy.

A pair of autonomous robots developed by Carnegie Mellon University's Robotics Institute will soon be driving through miles of pipes at the U.S. Department of Energy's former uranium enrichment plant in Piketon, Ohio, to identify uranium deposits on pipe walls. The CMU robot has demonstrated it can measure radiation levels more accurately from inside the pipe than is possible with external techniques. In addition to savings in labor costs, its use significantly reduces hazards to workers who otherwise must perform external measurements by hand, garbed in protective gear and using lifts or scaffolding to reach elevated pipes. DOE officials estimate the robots could save tens of millions of dollars in completing the characterization of uranium deposits at the Portsmouth Gaseous Diffusion Plant in Piketon, and save perhaps $50 million at a similar uranium enrichment plant in Paducah, Kentucky. "This will transform the way measurements of uranium deposits are made from now on," predicted William "Red" Whittaker, robotics professor and director of the Field Robotics Center.

File photo - An airplane flies over a drone during the Polar Bear Plunge on Coney Island in the Brooklyn borough of New York Jan. 1, 2015. While it seems unlikely that everyday drone hobbyists would want to make a beeline for their nearest nuclear facility to grab some aerial shots, the Federal Aviation Administration (FAA) has nevertheless announced a ban on drone flights over such locations in the U.S., namely: As you can see, they're mainly labs, while the Hanford Site, for example, is a mostly decommissioned nuclear production complex. Another of those listed, the Pantex Site, is an active nuclear weapons assembly and dismantlement plant. The restrictions, which come into force on December 29, have been put in place "to address concerns about unauthorized drone operations over seven Department of Energy (DOE) facilities," the FAA confirmed on its website. It added that "operators who violate the airspace restrictions may be subject to enforcement action, including potential civil penalties and criminal charges."