# Diagnosing Generalization Boundaries in AI-Based Vulnerability Detection via Calibrated Embedding Distances

arXiv: https://arxiv.org/abs/2610.14296 · HTML: https://mlsanity.com/paper/2610.14296/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 51 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 30 of 34)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Out-of-Distribution Detection with Deep Nearest Neighbors](https://mlsanity.com/paper/2204.06507/) (2022)
- [Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning](https://mlsanity.com/paper/2011.01403/) (2020)
- [Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning](https://mlsanity.com/paper/1803.04765/) (2018)
- [Whitening Sentence Representations for Better Semantics and Faster Retrieval](https://mlsanity.com/paper/2103.15316/) (2021)
- [Vulnerability Detection with Code Language Models: How Far Are We?](https://mlsanity.com/paper/2403.18624/) (2024)
- [The Adverse Effects of Code Duplication in Machine Learning Models of Code](https://mlsanity.com/paper/1812.06469/) (2018)
- [What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning](https://mlsanity.com/paper/1911.03090/) (2019)
- [Data Quality for Software Vulnerability Datasets](https://mlsanity.com/paper/2301.05456/) (2023)
- [LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights](https://mlsanity.com/paper/2502.07049/) (2025)
- [An Empirical Study of Deep Learning Models for Vulnerability Detection](https://mlsanity.com/paper/2212.08109/) (2022)
- [Finetuning Large Language Models for Vulnerability Detection](https://mlsanity.com/paper/2401.17010/) (2024)
- [Investigating Large Language Models for Code Vulnerability Detection: An Experimental Study](https://mlsanity.com/paper/2412.18260/) (2024)
- [Risk Assessment Framework for Code LLMs via Leveraging Internal States](https://mlsanity.com/paper/2504.14640/) (2025)
- [Characterizing Multi-Hunk Patches: Divergence, Proximity, and LLM Repair Challenges](https://mlsanity.com/paper/2506.04418/) (2025)
- [Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?](https://mlsanity.com/paper/2507.21817/) (2025)

## Abstract (arXiv)

High benchmark scores in learning-based vulnerability detection mask severe degradation under distribution shifts. This paper demonstrates that calibrated embedding geometry exposes these hidden generalization boundaries on syntactically similar vulnerable and patched code pairs. An evaluation of CodeBERT and Qwen2.5-Coder across pattern, project, and temporal shifts on a strictly paired dataset reveals three main findings. First, whitened intermediate-layer embeddings with local nearest-neighbour scoring separate unfamiliar samples with a mean out-of-distribution AUROC of 0.739 (RQ1). Second, distance scores reveal a shift-specific reliability gradient where accuracy drops by over 35 percentage points and cross-project shifts cause the sharpest degradation, even though temporal shifts drift geometrically farthest (RQ2). Third, false positives on patched code systematically correlate with geometric proximity to vulnerable training neighbourhoods, increasing from 9.4% in the lowest-risk decile to 58.8% in the highest (RQ3). These calibrated distances establish a diagnostic signal that maps representation geometry directly to model degradation without requiring auxiliary models.