Related papers: Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software

Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software

URL: http://arxiv.org/abs/2606.20502v1
Date: Thu, 18 Jun 2026 17:19:26 GMT
Title: Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software
Abstract summary: CWE-Trace is a framework for vulnerability detection built from 834 manually curated Linux kernel samples.<n>We evaluate eight vanilla LLMs and 15 LoRA fine-tuned variants across non-targeted detection, targeted detection, and CWE classification.
Score: 1.0026496861838445
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Whether LLMs scoring well on vulnerability benchmarks genuinely reason about security or merely pattern-match on contaminated data remains unresolved. We present CWE-Trace, a framework for LLM vulnerability detection built from 834 manually curated Linux kernel samples spanning 74 CWEs. The framework enforces a strict temporal split (pre-2025 historical set / post-cutoff leakage-free set), preserves context-aware vulnerable--patched pairs, and introduces two diagnostic metrics: the Directional Failure Index (DFI) and Hierarchical Distance and Direction (HDD). We evaluate eight vanilla LLMs and 15 LoRA fine-tuned variants across non-targeted detection, targeted detection, and CWE classification. Our analysis yields two key results. First, data contamination provides no measurable advantage. Function-level analysis shows that 84% of nominally contaminated samples carry no usable memorization signal: vulnerable functions are absent or cross-mapped across datasets, and ~31% of contaminated samples carry CWE misclassification. Second, backbone directional priors dominate fine-tuning. Models exhibit stable, systematic failure modes (DFI ranging from -85.5 to +94.8 pp) that persist from historical to post-cutoff data and resist correction. Fine-tuning shifts the output threshold without changing the decision policy. This is calibration without comprehension: output distributions adapt to training data while the underlying security reasoning remains absent. The weakest backbone at binary detection (DeepSeek-R1) gains the most in coarse CWE classification, revealing that detection and understanding are decoupled capabilities. The best detection score reaches only 52.1% (+2.1 pp above chance); exact CWE ranking remains below 1.3% Top-1 accuracy, confirming that current LLMs lack reliable security reasoning for systems software, regardless of fine-tuning strategy.

Related papers

Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations [55.76952683833966]
This paper proposes weighted CONCH (W-CONCH) and weighted CROC (W-CROC) to reduce confidence set size when data may be corrupted.<n>Experiments on image-based and real-world changepoint and root-cause benchmarks show that uncertainty-based weighting substantially reduces confidence set size.
arXiv Detail & Related papers (2026-07-29T05:16:59Z)
LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data [2.1443570696048906]
Large language models (LLMs) are increasingly applied to structured clinical data.<n>We compare Qwen 2.5 7B and XGBoost on a prediction task via attribution divergence analysis.
arXiv Detail & Related papers (2026-06-17T18:49:44Z)
CauTion: Knowing When to Trust LLMs for Ensemble Causal Discovery [51.07538881798502]
Large language models (LLMs) offer a promising source of domain knowledge to complement statistical inference.<n>We propose CauTion, a framework that reliably integrates LLM domain knowledge into an ensemble of statistical causal discovery algorithms.<n>CauTion consistently outperforms both data-centric and LLM-augmented baselines.
arXiv Detail & Related papers (2026-06-02T13:07:43Z)
Discovery of Hidden Miscalibration Regimes [52.452902154360565]
Models may be systematically overconfident on some kinds of inputs and underconfident on others.<n>We define the corresponding miscalibration field and propose a diagnostic framework for estimating it.<n>Our approach learns a calibration-aware representation of the input space and estimates signed local miscalibration by kernel smoothing in the learned geometry.
arXiv Detail & Related papers (2026-05-13T13:07:50Z)
Understanding NPM Malicious Package Detection: A Benchmark-Driven Empirical Analysis [10.599261033874884]
NPM ecosystem has become a primary target for software supply chain attacks.<n>We conduct a benchmark-driven empirical analysis of NPM malware detection.<n>We build a dataset of 6,420 malicious and 7,288 benign packages annotated with 11 behavior categories and 8 evasion techniques.
arXiv Detail & Related papers (2026-03-29T07:04:31Z)
Severe Domain Shift in Skeleton-Based Action Recognition:A Study of Uncertainty Failure in Real-World Gym Environments [0.0]
We present a systematic study of a severe domain shift using a novel Gym2D dataset and the UCF101 dataset.<n>Our work challenges standard deployment assumptions, providing a principled safety analysis of both semantic and geometric skeleton recognition deployment.
arXiv Detail & Related papers (2026-03-16T17:37:17Z)
BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
arXiv Detail & Related papers (2026-02-19T08:31:16Z)
When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift [0.0]
We present a comprehensive analysis using a benchmark of 18 datasets spanning harmful requests, jailbreaks, indirect prompt injections, and extraction attacks.<n>We propose Leave-One-Dataset-Out (LODO) evaluation to measure true out-of-distribution generalization.
arXiv Detail & Related papers (2026-02-15T14:21:43Z)
CLUE: Non-parametric Verification from Experience via Hidden-State Clustering [64.50919789875233]
We show that correctness of a solution is encoded as a geometrically separable signature within the trajectory of hidden activations.<n>ClUE consistently outperforms LLM-as-a-judge baselines and matches or exceeds modern confidence-based methods in reranking candidates.
arXiv Detail & Related papers (2025-10-02T02:14:33Z)
Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
arXiv Detail & Related papers (2025-09-26T23:40:47Z)
Probabilistic Soundness Guarantees in LLM Reasoning Chains [37.440902632372904]
Autoregressive Reasoning Entailment Stability (ARES) is a probabilistic framework that evaluates each reasoning step based solely on previously-verified premises.<n>ARES achieves state-of-the-art performance across four benchmarks and demonstrates superior robustness on very long synthetic reasoning chains.
arXiv Detail & Related papers (2025-07-17T09:40:56Z)
Conservative Prediction via Data-Driven Confidence Minimization [70.93946578046003]
In safety-critical applications of machine learning, it is often desirable for a model to be conservative. We propose the Data-Driven Confidence Minimization framework, which minimizes confidence on an uncertainty dataset.
arXiv Detail & Related papers (2023-06-08T07:05:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.