Robert Thomson

Alexander M. Berenbeim, Iain J. Cruickshank, Susmit Jha et al.

Quantitative characterizations and estimations of uncertainty are of fundamental importance in optimization and decision-making processes. Herein, we propose intuitive scores, which we call certainty and doubt, that can be used in both a Bayesian and frequentist framework to assess and compare the quality and uncertainty of predictions in (multi-)classification decision machine learning problems.

Xixi Wang, Jordanka Kovaceva, Miguel Costa et al.

Free-text crash narratives recorded in real-world crash databases have been shown to play a significant role in improving traffic safety. However, large-scale analyses remain difficult to implement as there are no documented tools that can batch process the unstructured, non standardized text content written by various authors with diverse experience and attention to detail. In recent years, Transformer-based pre-trained language models (PLMs), such as Bidirectional Encoder Representations from Transformers (BERT) and large language models (LLMs), have demonstrated strong capabilities across various natural language processing tasks. These models can extract explicit facts from crash narratives, but their performance declines on inference-heavy tasks in, for example, Crash Type identification, which can involve nearly 100 categories. Moreover, relying on closed LLMs through external APIs raises privacy concerns for sensitive crash data. Additionally, these black-box tools often underperform due to limited domain knowledge. Motivated by these challenges, we study whether compact open-source PLMs can support reasoning-intensive extraction from crash narratives. We target two challenging objectives: 1) identifying the Manner of Collision for a crash, and 2) Crash Type for each vehicle involved in the crash event from real-world crash narratives. To bridge domain gaps, we apply fine-tuning techniques to inject task-specific knowledge to LLMs with Low-Rank Adaption (LoRA) and BERT. Experiments on the authoritative real-world dataset Crash Investigation Sampling System (CISS) demonstrate that our fine-tuned compact models outperform strong closed LLMs, such as GPT-4o, while requiring only minimal training resources. Further analysis reveals that the fine-tuned PLMs can capture richer narrative details and even correct some mislabeled annotations in the dataset.

Eric Nunes, Casey Buto, Paulo Shakarian et al.

Identifying the tasks a given piece of malware was designed to perform (e.g. logging keystrokes, recording video, establishing remote access, etc.) is a difficult and time-consuming operation that is largely human-driven in practice. In this paper, we present an automated method to identify malware tasks. Using two different malware collections, we explore various circumstances for each - including cases where the training data differs significantly from test; where the malware being evaluated employs packing to thwart analytical techniques; and conditions with sparse training data. We find that this approach consistently out-performs the current state-of-the art software for malware task identification as well as standard machine learning approaches - often achieving an unbiased F1 score of over 0.9. In the near future, we look to deploy our approach for use by analysts in an operational cyber-security environment.