While de-identification models can help conceal the identity of the individual(s) mentioned in a document, they fail to address linkage risks, defined as the potential to map the de-identified text back to its source. One straightforward way to perform such linkages is to extract phrases from the de-identified document and then check their presence in the original dataset. This paper presents a method to counter search-based linkage attacks while preserving the semantic integrity of the text. The method proceeds in two steps. We first construct an inverted index of the N-grams occurring in the document collection, making it possible to efficiently determine which N-grams appear in less than $k$ documents (either alone or in combination with other N-grams). An LLM-based rewriter is then iteratively queried to reformulate those spans until linkage is no longer possible. Experimental results on a collection of court cases show that the method is able to effectively prevent search-based linkages while remaining faithful to the original content.

Automated interpretability aims to translate large language model (LLM) features into human understandable descriptions. However, these natural language feature descriptions are often vague, inconsistent, and require manual relabeling. In response, we introduce semantic regexes, structured language descriptions of LLM features. By combining primitives that capture linguistic and semantic feature patterns with modifiers for contextualization, composition, and quantification, semantic regexes produce precise and expressive feature descriptions. Across quantitative benchmarks and qualitative analyses, we find that semantic regexes match the accuracy of natural language while yielding more concise and consistent feature descriptions. Moreover, their inherent structure affords new types of analyses, including quantifying feature complexity across layers, scaling automated interpretability from insights into individual features to model-wide patterns. Finally, in user studies, we find that semantic regex descriptions help people build accurate mental models of LLM feature activations.

Face recognition in unconstrained environments such as surveillance, video, and web imagery must contend with extreme variation in pose, blur, illumination, and occlusion, where conventional visual quality metrics fail to predict whether inputs are truly recognizable to the deployed encoder. Existing FIQA methods typically rely on visual heuristics, curated annotations, or computationally intensive generative pipelines, leaving their predictions detached from the encoder's decision geometry. We introduce TransFIRA (Transfer Learning for Face Image Recognizability Assessment), a lightweight and annotation-free framework that grounds recognizability directly in embedding space. TransFIRA delivers three advances: (i) a definition of recognizability via class-center similarity (CCS) and class-center angular separation (CCAS), yielding the first natural, decision-boundary--aligned criterion for filtering and weighting; (ii) a recognizability-informed aggregation strategy that achieves state-of-the-art verification accuracy on BRIAR and IJB-C while nearly doubling correlation with true recognizability, all without external labels, heuristics, or backbone-specific training; and (iii) new extensions beyond faces, including encoder-grounded explainability that reveals how degradations and subject-specific factors affect recognizability, and the first recognizability-aware body recognition assessment. Experiments confirm state-of-the-art results on faces, strong performance on body recognition, and robustness under cross-dataset shifts. Together, these contributions establish TransFIRA as a unified, geometry-driven framework for recognizability assessment -- encoder-specific, accurate, interpretable, and extensible across modalities -- significantly advancing FIQA in accuracy, explainability, and scope.

Detecting surface landmines and unexploded ordnances (UXOs) using deep learning has shown promise in humanitarian demining. However, deterministic neural networks can be vulnerable to noisy conditions and adversarial attacks, leading to missed detection or misclassification. This study introduces the idea of uncertainty quantification through Monte Carlo (MC) Dropout, integrated into a fine-tuned ResNet-50 architecture for surface landmine and UXO classification, which was tested on a simulated dataset. Integrating the MC Dropout approach helps quantify epistemic uncertainty, providing an additional metric for prediction reliability, which could be helpful to make more informed decisions in demining operations. Experimental results on clean, adversarially perturbed, and noisy test images demonstrate the model's ability to flag unreliable predictions under challenging conditions. This proof-of-concept study highlights the need for uncertainty quantification in demining, raises awareness about the vulnerability of existing neural networks in demining to adversarial threats, and emphasizes the importance of developing more robust and reliable models for practical applications.

Multi-agent social interaction has clearly benefited from Large Language Models. However, current simulation systems still face challenges such as difficulties in scaling to diverse scenarios and poor reusability due to a lack of modular design. To address these issues, we designed and developed a modular, object-oriented framework that organically integrates various base classes through a hierarchical structure, harvesting scalability and reusability. We inherited the framework to realize common derived classes. Additionally, a memory summarization mechanism is proposed to filter and distill relevant information from raw memory data, prioritizing contextually salient events and interactions. By selecting and combining some necessary derived classes, we customized a specific simulated environment. Utilizing this simulated environment, we successfully simulated human interactions on social media, replicating real-world online social behaviors. The source code for the project will be released and evolve.

Recent advancements in jailbreaking large language models (LLMs), such as AutoDAN-Turbo, have demonstrated the power of automated strategy discovery. AutoDAN-Turbo employs a lifelong learning agent to build a rich library of attack strategies from scratch. While highly effective, its test-time generation process involves sampling a strategy and generating a single corresponding attack prompt, which may not fully exploit the potential of the learned strategy library. In this paper, we propose to further improve the attack performance of AutoDAN-Turbo through test-time scaling. We introduce two distinct scaling methods: Best-of-N and Beam Search. The Best-of-N method generates N candidate attack prompts from a sampled strategy and selects the most effective one based on a scorer model. The Beam Search method conducts a more exhaustive search by exploring combinations of strategies from the library to discover more potent and synergistic attack vectors. According to the experiments, the proposed methods significantly boost performance, with Beam Search increasing the attack success rate by up to 15.6 percentage points on Llama-3.1-70B-Instruct and achieving a nearly 60% relative improvement against the highly robust GPT-o4-mini compared to the vanilla method.

According to the U.S. National Institutes of Health, more than 3.4 million children experience speech disorders that require clinical intervention. The number of speech-language pathologists (SLPs) is roughly 20 times fewer than the number of affected children, highlighting a significant gap in children's care and a pressing need for technological support that improves the productivity of SLPs. State-of-the-art multimodal language models (MLMs) show promise for supporting SLPs, but their use remains underexplored largely due to a limited understanding of their performance in high-stakes clinical settings. To address this gap, we collaborate with domain experts to develop a taxonomy of real-world use cases of MLMs in speech-language pathologies. Building on this taxonomy, we introduce the first comprehensive benchmark for evaluating MLM across five core use cases, each containing 1,000 manually annotated data points. This benchmark includes robustness and sensitivity tests under various settings, including background noise, speaker gender, and accent. Our evaluation of 15 state-of-the-art MLMs reveals that no single model consistently outperforms others across all tasks. Notably, we find systematic disparities, with models performing better on male speakers, and observe that chain-of-thought prompting can degrade performance on classification tasks with large label spaces and narrow decision boundaries. Furthermore, we study fine-tuning MLMs on domain-specific data, achieving improvements of over 10\% compared to base models. These findings highlight both the potential and limitations of current MLMs for speech-language pathology applications, underscoring the need for further research and targeted development.

In medical coding, experts map unstructured clinical notes to alphanumeric codes for diagnoses and procedures. We introduce Code Like Humans: a new agentic framework for medical coding with large language models. It implements official coding guidelines for human experts, and it is the first solution that can support the full ICD-10 coding system (+70K labels). It achieves the best performance to date on rare diagnosis codes (fine-tuned discriminative classifiers retain an advantage for high-frequency codes, to which they are limited). Towards future work, we also contribute an analysis of system performance and identify its `blind spots' (codes that are systematically undercoded).

This is the author's version that has been accepted for publication in IEEE Network. The final version will be available at IEEE Xplore once published. Personal use of this material is permitted. Abstract --The Internet of Energy (IoE) integrates IoT -driven digital communication with power grids to enable efficient and sustainable energy systems. Still, its interconnectivity exposes critical infrastructure to sophisticated cyber threats, including adversarial attacks designed to bypass traditional safeguards. Unlike general IoT risks, IoE threats have heightened public safety consequences, demanding resilient solutions. From the networking-level safeguard perspective, we propose a Graph Structure Learning (GSL)-based safeguards framework that jointly optimizes graph topology and node representations to resist adversarial network model manipulation inherently. Through a conceptual overview, architectural discussion, and case study on a security dataset, we demonstrate GSL's superior robustness over representative methods, offering practitioners a viable path to secure IoE networks against evolving attacks. This work highlights the potential of GSL to enhance the resilience and reliability of future IoE networks for practitioners managing critical infrastructure. Lastly, we identify key open challenges and propose future research directions in this novel research area. Additional financial support was provided by National Taiwan University (NTU) and the NTU Core Consortium Project as part of the Higher Education Sprout Project by the Ministry of Education in Taiwan, under Grants NTU-CC-114L895501 and NTU-G0647.

This thesis investigates whether large language models (LLMs) can be guided to simulate a consistent personality through prompt engineering. The study explores this concept within the context of a chatbot designed for Speech-Language Pathology (SLP) student training, specifically focused on gender-affirming voice therapy. The chatbot, named Monae Jackson, was created to represent a 32-year-old transgender woman and engage in conversations simulating client-therapist interactions. Findings suggest that with prompt engineering, the chatbot maintained a recognizable and consistent persona and had a distinct personality based on the Big Five Personality test. These results support the idea that prompt engineering can be used to simulate stable personality characteristics in AI chatbots.