Software logs are messages recorded during the execution of a software system that provide crucial run-time information about events and activities. Although software logs have a critical role in software maintenance and operation tasks, publicly accessible log datasets remain limited, hindering advance in log analysis research and practices. The presence of sensitive information, particularly Personally Identifiable Information (PII) and quasi-identifiers, introduces serious privacy and re-identification risks, discouraging the publishing and sharing of real-world logs. In practice, log anonymization techniques primarily rely on regular expression patterns, which involve manually crafting rules to identify and replace sensitive information. However, these regex-based approaches suffer from significant limitations, such as extensive manual efforts and poor generalizability across diverse log formats and datasets. To mitigate these limitations, we introduce SDLog, a deep learning-based framework designed to identify sensitive information in software logs. Our results show that SDLog overcomes regex limitations and outperforms the best-performing regex patterns in identifying sensitive information. With only 100 fine-tuning samples from the target dataset, SDLog can correctly identify 99.5% of sensitive attributes and achieves an F1-score of 98.4%. To the best of our knowledge, this is the first deep learning alternative to regex-based methods in software log anonymization.

AI systems deployed in high - consequence environments -- such as defense, intelligence, and disaster response -- must detect rare, high - impact events under operational constraints. Traditional annotation strategies that emphasize volume over value fail in these s ettings, introducing redundancy, noise, and risk. This paper presents smart - sizing, a strategic approach to training data curation that prioritizes informational value, label diversity, and model - guided selection. We introduce Adaptive Label Optimization ( ALO) as an implementation framework for smart - sizing, combining pre - labeling, human - in - the - loop feedback, disagreement analysis, and marginal utility - based stopping rules. Through empirical experiments, we show that models trained on only 20 - 40% of a curated dataset match or exceed the performance of full - data baselines, particularly in rare class recall and edge - case generalization. We also demonstrate how systematic labeli ng errors embedded in both training and validation sets can produce misleading model evaluations, underscoring the need for internal audit mechanisms and data governance. Smart - sizing reframes annotation from a static task to a feedback - driven protocol aligned with operational goals. It offers a measurable path to improving AI robustness while reducing labeling cost, enabling teams to label what matters -- and stop when it no longer helps.

Ensuring the reliability and safety of machine learning models in open-world deployment is a central challenge in AI safety. This thesis develops both algorithmic and theoretical foundations to address key reliability issues arising from distributional uncertainty and unknown classes, from standard neural networks to modern foundation models like large language models (LLMs). Traditional learning paradigms, such as empirical risk minimization (ERM), assume no distribution shift between training and inference, often leading to overconfident predictions on out-of-distribution (OOD) inputs. This thesis introduces novel frameworks that jointly optimize for in-distribution accuracy and reliability to unseen data. A core contribution is the development of an unknown-aware learning framework that enables models to recognize and handle novel inputs without labeled OOD data. We propose new outlier synthesis methods, VOS, NPOS, and DREAM-OOD, to generate informative unknowns during training. Building on this, we present SAL, a theoretical and algorithmic framework that leverages unlabeled in-the-wild data to enhance OOD detection under realistic deployment conditions. These methods demonstrate that abundant unlabeled data can be harnessed to recognize and adapt to unforeseen inputs, providing formal reliability guarantees. The thesis also extends reliable learning to foundation models. We develop HaloScope for hallucination detection in LLMs, MLLMGuard for defending against malicious prompts in multimodal models, and data cleaning methods to denoise human feedback used for better alignment. These tools target failure modes that threaten the safety of large-scale models in deployment. Overall, these contributions promote unknown-aware learning as a new paradigm, and we hope it can advance the reliability of AI systems with minimal human efforts.

Consider this prompt "Draw a unicorn with two horns". Should large language models (LLMs) recognize that a unicorn has only one horn by definition and ask users for clarifications, or proceed to generate something anyway? We introduce concept incongruence to capture such phenomena where concept boundaries clash with each other, either in user prompts or in model representations, often leading to under-specified or mis-specified behaviors. In this work, we take the first step towards defining and analyzing model behavior under concept incongruence. Focusing on temporal boundaries in the Role-Play setting, we propose three behavioral metrics--abstention rate, conditional accuracy, and answer rate--to quantify model behavior under incongruence due to the role's death. We show that models fail to abstain after death and suffer from an accuracy drop compared to the Non-Role-Play setting. Through probing experiments, we identify two main causes: (i) unreliable encoding of the "death" state across different years, leading to unsatisfactory abstention behavior, and (ii) role playing causes shifts in the model's temporal representations, resulting in accuracy drops. We leverage these insights to improve consistency in the model's abstention and answer behaviors. Our findings suggest that concept incongruence leads to unexpected model behaviors and point to future directions on improving model behavior under concept incongruence.

The pursuit of alpha returns that exceed market benchmarks has undergone a profound transformation, evolving from intuition-driven investing to autonomous, AI powered systems. This paper introduces a comprehensive five stage taxonomy that traces this progression across manual strategies, statistical models, classical machine learning, deep learning, and agentic architectures powered by large language models (LLMs). Unlike prior surveys focused narrowly on modeling techniques, this review adopts a system level lens, integrating advances in representation learning, multimodal data fusion, and tool augmented LLM agents. The strategic shift from static predictors to contextaware financial agents capable of real time reasoning, scenario simulation, and cross modal decision making is emphasized. Key challenges in interpretability, data fragility, governance, and regulatory compliance areas critical to production deployment are examined. The proposed taxonomy offers a unified framework for evaluating maturity, aligning infrastructure, and guiding the responsible development of next generation alpha systems.

Over the years, ComBAT has become the standard method for harmonizing MRI-derived measurements, with its ability to compensate for site-related additive and multiplicative biases while preserving biological variability. However, ComBAT relies on a set of assumptions that, when violated, can result in flawed harmonization. In this paper, we thoroughly review ComBAT's mathematical foundation, outlining these assumptions, and exploring their implications for the demographic composition necessary for optimal results. Through a series of experiments involving a slightly modified version of ComBAT called Pairwise-ComBAT tailored for normative modeling applications, we assess the impact of various population characteristics, including population size, age distribution, the absence of certain covariates, and the magnitude of additive and multiplicative factors. Based on these experiments, we present five essential recommendations that should be carefully considered to enhance consistency and supporting reproducibility, two essential factors for open science, collaborative research, and real-life clinical deployment.

Predicting crash events is crucial for understanding crash distributions and their contributing factors, thereby enabling the design of proactive traffic safety policy interventions. However, existing methods struggle to interpret the complex interplay among various sources of traffic crash data, including numeric characteristics, textual reports, crash imagery, environmental conditions, and driver behavior records. As a result, they often fail to capture the rich semantic information and intricate interrelationships embedded in these diverse data sources, limiting their ability to identify critical crash risk factors. In this research, we propose TrafficSafe, a framework that adapts LLMs to reframe crash prediction and feature attribution as text-based reasoning. A multi-modal crash dataset including 58,903 real-world reports together with belonged infrastructure, environmental, driver, and vehicle information is collected and textualized into TrafficSafe Event Dataset. By customizing and fine-tuning LLMs on this dataset, the TrafficSafe LLM achieves a 42% average improvement in F1-score over baselines. To interpret these predictions and uncover contributing factors, we introduce TrafficSafe Attribution, a sentence-level feature attribution framework enabling conditional risk analysis. Findings show that alcohol-impaired driving is the leading factor in severe crashes, with aggressive and impairment-related behaviors having nearly twice the contribution for severe crashes compared to other driver behaviors. Furthermore, TrafficSafe Attribution highlights pivotal features during model training, guiding strategic crash data collection for iterative performance improvements. The proposed TrafficSafe offers a transformative leap in traffic safety research, providing a blueprint for translating advanced AI technologies into responsible, actionable, and life-saving outcomes.

A routine training flight over Arizona in January 2023 took an unusual turn when a U.S. Air Force F-16D was struck by what was initially reported as an unidentified object, but now U.S. defense officials say was a small drone. Fox News confirmed that the incident, which occurred near Gila Bend, Arizona, on Jan. 19, 2023, was a routine training mission and was witnessed by the instructor pilot seated in the rear of the two-seat aircraft. According to a U.S. defense official, the pilot observed a "mostly white and orange object" collide with the left side of the aircraft canopy, the transparent covering over the cockpit. Initially, the object was thought to be a bird, a common hazard for aircraft. But after conducting checks during the flight and a detailed inspection upon landing at Tucson International Airport, the crew found "zero evidence" of a bird strike.

CNN host Jake Tapper told Joe Scarborough during a Wednesday conversation on "Morning Joe" that former President Biden made an effort to convince the MSNBC host that he was fit to run for re-election. The Washington Post editorial board called for more oversight of the Oval Office on Wednesday to ensure a cover-up of the president's health doesn't happen again following revelations in a bombshell book alleging the White House hid former President Joe Biden's decline from the public. "It now seems that, for a considerable time, Biden might have lacked the stamina and cognitive capacity the job demands -- and that his family and closest aides concealed this from the public," the paper's editorial board wrote. "Their apparent decision to put personal loyalties ahead of their duty to the country must be reckoned with. A legal mechanism should be considered to ensure that this doesn't happen again," the board proposed.

Although the Cannes Film Festival is the world's most prestigious movie showcase, its spotlight rarely falls on nonfiction film. Years go by without a single documentary competing for its biggest honor, the Palme d'Or, and there is no separate documentary prize. Juliette Binoche, the president of this year's jury, devoted part of her opening-night remarks to Fatma Hassona, the Palestinian photojournalist who was killed in an Israeli airstrike the day after it was announced that her documentary Put Your Soul on Your Hand and Walk would be premiering at Cannes. But the film itself was slotted into a low-profile sidebar devoted to independent productions. The festival did, however, roll out the red carpet for The Six Billion Dollar Man, Eugene Jarecki's portrait of WikiLeaks founder Julian Assange, which premiered out of competition on Wednesday evening.