Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy concerns. In this work, we conduct the first comprehensive study evaluating the vulnerability of fine-tuned LLMs to membership inference attacks (MIAs). Our empirical analysis demonstrates that MIAs exploit the loss reduction during fine-tuning, making them highly effective in revealing membership information. These findings motivate the development of our defense. We propose SOFT (\textbf{S}elective data \textbf{O}bfuscation in LLM \textbf{F}ine-\textbf{T}uning), a novel defense technique that mitigates privacy leakage by leveraging influential data selection with an adjustable parameter to balance utility preservation and privacy protection. Our extensive experiments span six diverse domains and multiple LLM architectures and scales. Results show that SOFT effectively reduces privacy risks while maintaining competitive model performance, offering a practical and scalable solution to safeguard sensitive information in fine-tuned LLMs.

This paper presents a comprehensive analysis of an enhanced asynchronous AdaBoost framework for federated learning (FL), focusing on its application across five distinct domains: computer vision on edge devices, blockchain - based model transparency, on - device mobile personalization, IoT anomaly detection, and federated healthcare diagnostics. The proposed algorithm incorporates adaptive communication scheduling and delayed weight compensation to reduce synchronization frequency and communication overhead while preserving or improving model accuracy. We examine how these innovations improve communic ation efficiency, scalability, convergence, and robustness in each domain. Comparative metrics including training time, communication overhead, convergence iterations, and classification accuracy are evaluated using data and estimates derived from Oghlukya n's enhanced AdaBoost framework. Empirical results show, for example, training time reductions on the order of 20 - 35% and communication overhead reductions of 30 - 40% compared to baseline AdaBoost, with convergence achieved in significantly fewer boosting r ounds. Tables and charts summarize these improvements by domain. Mathematical formulations of the adaptive scheduling rule and error - driven synchronization thresholds are provided. Overall, the enhanced AdaBoost exhibits markedly improved efficiency and ro bustness across diverse FL scenarios, suggesting broad applicability of the approach.

We consider a high-probability non-asymptotic confidence estimation in the $\ell^2$-regularized non-linear least-squares setting with fixed design. In particular, we study confidence estimation for local minimizers of the regularized training loss. We show a pointwise confidence bound, meaning that it holds for the prediction on any given fixed test input $x$. Importantly, the proposed confidence bound scales with similarity of the test input to the training data in the implicit feature space of the predictor (for instance, becoming very large when the test input lies far outside of the training data). This desirable last feature is captured by the weighted norm involving the inverse-Hessian matrix of the objective function, which is a generalized version of its counterpart in the linear setting, $x^{\top} \text{Cov}^{-1} x$. Our generalized result can be regarded as a non-asymptotic counterpart of the classical confidence interval based on asymptotic normality of the MLE estimator. We propose an efficient method for computing the weighted norm, which only mildly exceeds the cost of a gradient computation of the loss function. Finally, we complement our analysis with empirical evidence showing that the proposed confidence bound provides better coverage/width trade-off compared to a confidence estimation by bootstrapping, which is a gold-standard method in many applications involving non-linear predictors such as neural networks.

Having designed a VQVAE that maps digital radio waveforms into discrete latent space, and yields a perfectly classifiable reconstruction of the original data, we here analyze the attack suppressing properties of VQVAE when an adversarial attack is performed on high-SNR radio-frequency (RF) data-points. To target amplitude modulations from a subset of digitally modulated waveform classes, we first create adversarial attacks that preserve the phase between the in-phase and quadrature component whose values are adversarially changed. We compare them with adversarial attacks of the same intensity where phase is not preserved. We test the classification accuracy of such adversarial examples on a classifier trained to deliver 100% accuracy on the original data. To assess the ability of VQVAE to suppress the strength of the attack, we evaluate the classifier accuracy on the reconstructions by VQVAE of the adversarial datapoints and show that VQVAE substantially decreases the effectiveness of the attack. We also compare the I/Q plane diagram of the attacked data, their reconstructions and the original data. Finally, using multiple methods and metrics, we compare the probability distribution of the VQVAE latent space with and without attack. Varying the attack strength, we observe interesting properties of the discrete space, which may help detect the attacks.

Speaker anonymization systems hide the identity of speakers while preserving other information such as linguistic content and emotions. To evaluate their privacy benefits, attacks in the form of automatic speaker verification (ASV) systems are employed. In this study, we assess the impact of intra-speaker linguistic content similarity in the attacker training and evaluation datasets, by adapting BERT, a language model, as an ASV system. On the VoicePrivacy Attacker Challenge datasets, our method achieves a mean equal error rate (EER) of 35%, with certain speakers attaining EERs as low as 2%, based solely on the textual content of their utterances. Our explainability study reveals that the system decisions are linked to semantically similar keywords within utterances, stemming from how LibriSpeech is curated. Our study suggests reworking the VoicePrivacy datasets to ensure a fair and unbiased evaluation and challenge the reliance on global EER for privacy evaluations.

Alzheimer's dementia (AD) is a neurodegenerative disorder with cognitive decline that commonly impacts language ability. This work extends the paired perplexity approach to detecting AD by using a recent large language model (LLM), the instruction-following version of Mistral-7B. We improve accuracy by an average of 3.33% over the best current paired perplexity method and by 6.35% over the top-ranked method from the ADReSS 2020 challenge benchmark. Our further analysis demonstrates that the proposed approach can effectively detect AD with a clear and interpretable decision boundary in contrast to other methods that suffer from opaque decision-making processes. Finally, by prompting the fine-tuned LLMs and comparing the model-generated responses to human responses, we illustrate that the LLMs have learned the special language patterns of AD speakers, which opens up possibilities for novel methods of model interpretation and data augmentation.

Millions of players engage daily in competitive online games, communicating through in-game chat. Prior research has focused on detecting relatively small volumes of toxic content using various Natural Language Processing (NLP) techniques for the purpose of moderation. However, recent studies emphasize the importance of detecting prosocial communication, which can be as crucial as identifying toxic interactions. Recognizing prosocial behavior allows for its analysis, rewarding, and promotion. Unlike toxicity, there are limited datasets, models, and resources for identifying prosocial behaviors in game-chat text. In this work, we employed unsupervised discovery combined with game domain expert collaboration to identify and categorize prosocial player behaviors from game chat. We further propose a novel Self-Anchored Attention Model (SAAM) which gives 7.9% improvement compared to the best existing technique. The approach utilizes the entire training set as "anchors" to help improve model performance under the scarcity of training data. This approach led to the development of the first automated system for classifying prosocial behaviors in in-game chats, particularly given the low-resource settings where large-scale labeled data is not available. Our methodology was applied to one of the most popular online gaming titles - Call of Duty(R): Modern Warfare(R)II, showcasing its effectiveness. This research is novel in applying NLP techniques to discover and classify prosocial behaviors in player in-game chat communication. It can help shift the focus of moderation from solely penalizing toxicity to actively encouraging positive interactions on online platforms.

The performance of perception systems in autonomous driving systems (ADS) is strongly influenced by object distance, scene dynamics, and environmental conditions such as weather. AI-based perception outputs are inherently stochastic, with variability driven by these external factors, while traditional evaluation metrics remain static and event-independent, failing to capture fluctuations in confidence over time. In this work, we introduce the Perception Characteristics Distance (PCD) -- a novel evaluation metric that quantifies the farthest distance at which an object can be reliably detected, incorporating uncertainty in model outputs. To support this, we present the SensorRainFall dataset, collected on the Virginia Smart Road using a sensor-equipped vehicle (cameras, radar, LiDAR) under controlled daylight-clear and daylight-rain scenarios, with precise ground-truth distances to the target objects. Statistical analysis reveals the presence of change points in the variance of detection confidence score with distance. By averaging the PCD values across a range of detection quality thresholds and probabilistic thresholds, we compute the mean PCD (mPCD), which captures the overall perception characteristics of a system with respect to detection distance. Applying state-of-the-art perception models shows that mPCD captures meaningful reliability differences under varying weather conditions -- differences that static metrics overlook. PCD provides a principled, distribution-aware measure of perception performance, supporting safer and more robust ADS operation, while the SensorRainFall dataset offers a valuable benchmark for evaluation. The SensorRainFall dataset is publicly available at https://www.kaggle.com/datasets/datadrivenwheels/sensorrainfall, and the evaluation code is open-sourced at https://github.com/datadrivenwheels/PCD_Python.

Antibody-facilitated immune responses are central to the body's defense against pathogens, viruses, and other foreign invaders. The ability of antibodies to specifically bind and neutralize antigens is vital for maintaining immunity. Over the past few decades, bioengineering advancements have significantly accelerated therapeutic antibody development. These antibody-derived drugs have shown remarkable efficacy, particularly in treating cancer, SARS-CoV-2, autoimmune disorders, and infectious diseases. Traditionally, experimental methods for affinity measurement have been time-consuming and expensive. With the advent of artificial intelligence, in silico medicine has been revolutionized; recent developments in machine learning, particularly the use of large language models (LLMs) for representing antibodies, have opened up new avenues for AI-based design and improved affinity prediction. Herein, we present an advanced antibody-antigen binding affinity prediction model (LlamaAffinity), leveraging an open-source Llama 3 backbone and antibody sequence data sourced from the Observed Antibody Space (OAS) database. The proposed approach shows significant improvement over existing state-of-the-art (SOTA) methods (AntiFormer, AntiBERTa, AntiBERTy) across multiple evaluation metrics. Specifically, the model achieved an accuracy of 0.9640, an F1-score of 0.9643, a precision of 0.9702, a recall of 0.9586, and an AUC-ROC of 0.9936. Moreover, this strategy unveiled higher computational efficiency, with a five-fold average cumulative training time of only 0.46 hours, significantly lower than in previous studies.

Having a unified, coherent taxonomy is essential for effective knowledge representation in domain-specific applications as diverse terminologies need to be mapped to underlying concepts. Traditional manual approaches to taxonomy alignment rely on expert review of concept pairs, but this becomes prohibitively expensive and time-consuming at scale, while subjective interpretations often lead to expert disagreements. Existing automated methods for taxonomy alignment have shown promise but face limitations in handling nuanced semantic relationships and maintaining consistency across different domains. These approaches often struggle with context-dependent concept mappings and lack transparent reasoning processes. We propose a novel framework that combines large language models (LLMs) with expert calibration and iterative prompt optimization to automate taxonomy alignment. Our method integrates expert-labeled examples, multi-stage prompt engineering, and human validation to guide LLMs in generating both taxonomy linkages and supporting rationales. In evaluating our framework on a domain-specific mapping task of concept essentiality, we achieved an F1-score of 0.97, substantially exceeding the human benchmark of 0.68. These results demonstrate the effectiveness of our approach in scaling taxonomy alignment while maintaining high-quality mappings and preserving expert oversight for ambiguous cases.