arXiv subjects

Gregory D. Vetaw

Publications and source records attributed to Gregory D. Vetaw.

4 recordsLinked to original sources

arXiv2026

Deep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models

Activation steering modifies LLM behavior at inference time, but identifying where and how strongly to steer remains manual. We introduce Deep Noir, a framework that uses Logit Lens convergence and causal head-level attribution to autonomously discover optimal steering parameters. Across three scales (1B x 3, 2-3B x 2, and 7-9B x 4), our engine achieves 16.7 percentage-point improvement on spam at 1B (standard deviation 4.7; 39 runs), with gains increasing to 21 to 42 percentage points at 7-9B across four architectures. On SST-2 sentiment, it achieves a 13.1 percentage-point improvement with zero code changes. Mechanistic grounding enables automated discovery of intervention points that generalize across tasks and architectures. On sentiment, RepE without head masking fails to improve over baseline, while Deep Noir improves all models (p less than 0.01). We further show that steering creates a predictable prompt-injection attack surface whose vulnerability increases monotonically with steering magnitude. This finding is relevant to agent systems deploying steered classifiers.

cs.AI↗

arXiv2026

LoRA Enhanced Contrastive Learning with SAS Vision Transformers

Automatic target recognition (ATR) with synthetic aperture sonar (SAS) supports advanced naval capabilities, but deep learning is constrained by scarce target imagery, background clutter, and human-in-the-loop assessment. We adapt DINOv3 Vision Transformer (ViT) models to underwater SAS ATR using a three-stage parameter-efficient framework. Stage 1 uses Low-Rank Adaptation (LoRA) while freezing the ViT backbone, bridging the gap between natural-image pretraining and underwater acoustic propagation. Stage 2 uses hard-negative mining to strengthen the decision boundary against acoustic mimics, including rocks and sediment formations resembling man-made targets. Stage 3 uses Supervised Contrastive Learning (SupCon) to separate target and clutter representations. We evaluate at-sea SAS data using a mission-level geographic split, compare all arms at 85 percent test recall, and repeat each comparison over three random seeds. LoRA accounts for the primary effect, increasing area under the precision-recall curve (AUPRC) from 0.300 to 0.679 +/- 0.027 using the same frozen backbone. Rank 4 achieves this result while training only 0.26 percent of weights. Neither refinement stage exceeds its matched control: hard-negative mining changes AUPRC by -0.0045 +/- 0.0119 versus an equal-size random curriculum, and SupCon changes AUPRC by +0.0002 +/- 0.0096 versus the preceding stage. These null results indicate that mining occurred on data the encoder had already fit and that supervised stages had already imposed most target-clutter geometry. One efficient adaptation stage is sufficient; stacked refinement is not.

cs.AI↗

arXiv2026

A Comparison of Data Augmentation Methods for Training Deep Neural Networks on Synthetic Aperture Sonar

In this work we study Automatic Target Recognition (ATR) for Synthetic Aperture Sonar (SAS) data with a focus on deep neural networks (DNNs). The main challenge in training DNNs for SAS-ATR arises from the limited quantity of labeled target examples due to the significant costs and time required to collect real-world SAS data. One successful general strategy for mitigating the problem of limited training data is augmentation, which generates additional synthetic training data by introducing realistic variations to available data. Prior research has investigated a variety of augmentation strategies for SAS-ATR, including conventional image augmentations (e.g., contrast changes, cropping) as well as augmentations motivated the specific physics of SAS data. Building on prior work, we systematically compare many of these existing augmentation strategies for training DNNs for SAS-ATR. We also investigate the impact of augmentation when combined with modern DNN architectures such as transformers. The results indicate that augmentation can improve target recognition accuracy, although benefits vary, and not all augmentations are beneficial.

cs.LG↗

arXiv2026

Diagnosing Generalization Failures in Fine-Tuned LLMs: A Cross-Architectural Study on Phishing Detection

The practice of fine-tuning Large Language Models (LLMs) has achieved state-of-the-art performance on specialized tasks, yet diagnosing why these models become brittle and fail to generalize remains a critical open problem. To address this, we introduce and apply a multi-layered diagnostic framework to a cross-architectural study. We fine-tune Llama 3.1 8B, Gemma 2 9B, and Mistral models on a high-stakes phishing detection task and use SHAP analysis and mechanistic interpretability to uncover the root causes of their generalization failures. Our investigation reveals three critical findings: (1) Generalization is driven by a powerful synergy between architecture and data diversity. The Gemma 2 9B model achieves state-of-the-art performance (>91\% F1), but only when trained on a stylistically diverse ``generalist'' dataset. (2) Generalization is highly architecture-dependent. We diagnose a specific failure mode in Llama 3.1 8B, which performs well on a narrow domain but cannot integrate diverse data, leading to a significant performance drop. (3) Some architectures are inherently more generalizable. The Mistral model proves to be a consistent and resilient performer across multiple training paradigms. By pinpointing the flawed heuristics responsible for these failures, our work provides a concrete methodology for diagnosing and understanding generalization failures, underscoring that reliable AI requires deep validation of the interplay between architecture, data, and training strategy.

cs.AI↗