Statistical Runtime Verification for LLMs via Robustness Estimation

• URL: http://arxiv.org/abs/2504.17723v2
• Date: Thu, 24 Jul 2025 08:03:09 GMT
• Title: Statistical Runtime Verification for LLMs via Robustness Estimation
• Authors: Natan Levy, Adiel Ashrov, Guy Katz,
• Abstract summary: Adversarial robustness verification is essential for ensuring the safe deployment of Large Language Models (LLMs) in runtime-critical applications.<n>This paper presents a case study adapting and extending the RoMA statistical verification framework to assess its feasibility as an online runtime robustness monitor for LLMs in black-box deployment settings.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adversarial robustness verification is essential for ensuring the safe deployment of Large Language Models (LLMs) in runtime-critical applications. However, formal verification techniques remain computationally infeasible for modern LLMs due to their exponential runtime and white-box access requirements. This paper presents a case study adapting and extending the RoMA statistical verification framework to assess its feasibility as an online runtime robustness monitor for LLMs in black-box deployment settings. Our adaptation of RoMA analyzes confidence score distributions under semantic perturbations to provide quantitative robustness assessments with statistically validated bounds. Our empirical validation against formal verification baselines demonstrates that RoMA achieves comparable accuracy (within 1\% deviation), and reduces verification times from hours to minutes. We evaluate this framework across semantic, categorial, and orthographic perturbation domains. Our results demonstrate RoMA's effectiveness for robustness monitoring in operational LLM deployments. These findings point to RoMA as a potentially scalable alternative when formal methods are infeasible, with promising implications for runtime verification in LLM-based systems.

Related papers

• Phishing Detection in the Gen-AI Era: Quantized LLMs vs Classical Models [1.4999444543328293]
  Phishing attacks are becoming increasingly sophisticated, underscoring the need for detection systems that strike a balance between high accuracy and computational efficiency.<n>This paper presents a comparative evaluation of traditional Machine Learning (ML), Deep Learning (DL), and quantized small- parameter Large Language Models (LLMs) for phishing detection.<n>We show that while LLMs currently underperform compared to ML and DL methods in terms of raw accuracy, they exhibit strong potential for identifying subtle, context-based phishing cues.
  arXiv  Detail & Related papers  (2025-07-10T04:01:52Z)
• Statistical Hypothesis Testing for Auditing Robustness in Language Models [49.1574468325115]
  We introduce distribution-based perturbation analysis, a framework that reformulates perturbation analysis as a frequentist hypothesis testing problem.<n>We construct empirical null and alternative output distributions within a low-dimensional semantic similarity space via Monte Carlo sampling.<n>We show how we can quantify response changes, measure true/false positive rates, and evaluate alignment with reference models.
  arXiv  Detail & Related papers  (2025-06-09T17:11:07Z)
• Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge [0.0]
  Large Language Models (LLMs) have revolutionized artificial intelligence, driving advancements in machine translation, summarization, and conversational agents.<n>Recent studies indicate that LLMs remain vulnerable to adversarial attacks designed to elicit biased responses.<n>This work proposes a scalable benchmarking framework to evaluate LLM robustness against adversarial bias elicitation.
  arXiv  Detail & Related papers  (2025-04-10T16:00:59Z)
• Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models [13.216398753024182]
  Large Language Models (LLMs) and Vision-Language Models (VLMs) have become essential to general artificial intelligence.<n>We propose a novel stability measure for LLMs inspired by statistical methods rooted in information geometry.<n>Our results demonstrate the utility of our measure in identifying salient parameters and detecting vulnerable regions in input images or critical dimensions in token embeddings.
  arXiv  Detail & Related papers  (2025-03-28T16:23:59Z)
• Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling [48.15636223774418]
  Large language models (LLMs) frequently hallucinate due to misaligned self-awareness.<n>Existing approaches mitigate hallucinations via uncertainty estimation or query rejection.<n>We propose the Explicit Knowledge Boundary Modeling framework to integrate fast and slow reasoning systems.
  arXiv  Detail & Related papers  (2025-03-04T03:16:02Z)
• FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Models [79.41859481668618]
  Large Language Models (LLMs) have significantly advanced the fact-checking studies.<n>Existing automated fact-checking evaluation methods rely on static datasets and classification metrics.<n>We introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs' fact-checking capabilities.
  arXiv  Detail & Related papers  (2025-02-25T07:44:22Z)
• Bridging Interpretability and Robustness Using LIME-Guided Model Refinement [0.0]
  Local Interpretable Model-Agnostic Explanations (LIME) systematically enhance model robustness.<n> Empirical evaluations on multiple benchmark datasets demonstrate that LIME-guided refinement not only improves interpretability but also significantly enhances resistance to adversarial perturbations and generalization to out-of-distribution data.
  arXiv  Detail & Related papers  (2024-12-25T17:32:45Z)
• On Adversarial Robustness and Out-of-Distribution Robustness of Large Language Models [0.16874375111244325]
  We investigate the correlation between adversarial robustness and OOD robustness in large language models (LLMs)<n>Our findings highlight nuanced interactions between adversarial robustness and OOD robustness, with results indicating limited transferability.<n>Further research is needed to evaluate these interactions across larger models and varied architectures.
  arXiv  Detail & Related papers  (2024-12-13T20:04:25Z)
• Is it the model or the metric -- On robustness measures of deeplearning models [2.8169948004297565]
  We revisit robustness investigating the sufficiency of robust accuracy (RA) within the context of deepfake detection.<n>We present a comparison of RA and RR and demonstrate that despite similar RA between models, the models show varying RR under different tolerance (perturbation) levels.
  arXiv  Detail & Related papers  (2024-12-13T02:26:58Z)
• The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance? [1.3810901729134184]
  Large Language Models (LLMs) excel at standardized tests while failing to demonstrate genuine language understanding and adaptability.<n>Our systematic analysis of NLP evaluation frameworks reveals pervasive vulnerabilities across the evaluation spectrum.<n>We lay the groundwork for new evaluation methods that resist manipulation, minimize data contamination, and assess domain-specific tasks.
  arXiv  Detail & Related papers  (2024-12-02T20:49:21Z)
• Exploring Automatic Cryptographic API Misuse Detection in the Era of LLMs [60.32717556756674]
  This paper introduces a systematic evaluation framework to assess Large Language Models in detecting cryptographic misuses. Our in-depth analysis of 11,940 LLM-generated reports highlights that the inherent instabilities in LLMs can lead to over half of the reports being false positives. The optimized approach achieves a remarkable detection rate of nearly 90%, surpassing traditional methods and uncovering previously unknown misuses in established benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T15:31:26Z)
• Benchmarks as Microscopes: A Call for Model Metrology [76.64402390208576]
  Modern language models (LMs) pose a new challenge in capability assessment. To be confident in our metrics, we need a new discipline of model metrology.
  arXiv  Detail & Related papers  (2024-07-22T17:52:12Z)
• Towards Evaluating the Robustness of Visual State Space Models [63.14954591606638]
  Vision State Space Models (VSSMs) have demonstrated remarkable performance in visual perception tasks. However, their robustness under natural and adversarial perturbations remains a critical concern. We present a comprehensive evaluation of VSSMs' robustness under various perturbation scenarios.
  arXiv  Detail & Related papers  (2024-06-13T17:59:44Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training [105.02614392553198]
  We propose Robustifying LMs via Adversarial perturbation with Selective Training (RoAST) RoAST incorporates two important sources for the model robustness, robustness on the perturbed inputs and generalizable knowledge in pre-trained LMs. We demonstrate the effectiveness of RoAST compared to state-of-the-art fine-tuning methods on six different types of LMs.
  arXiv  Detail & Related papers  (2023-12-07T04:23:36Z)
• Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
  In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
  arXiv  Detail & Related papers  (2023-11-15T05:58:35Z)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)
• Assessing the Reliability of Large Language Model Knowledge [78.38870272050106]
  Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. How do we evaluate the capabilities of LLMs to consistently produce factually correct answers? We propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability.
  arXiv  Detail & Related papers  (2023-10-15T12:40:30Z)
• StaDRe and StaDRo: Reliability and Robustness Estimation of ML-based Forecasting using Statistical Distance Measures [0.476203519165013]
  This work focuses on the use of SafeML for time series data, and on reliability and robustness estimation of ML-forecasting methods using statistical distance measures. We propose SDD-based Reliability Estimate (StaDRe) and SDD-based Robustness (StaDRo) measures. With the help of a clustering technique, the similarity between the statistical properties of data seen during training and the forecasts is identified.
  arXiv  Detail & Related papers  (2022-06-17T19:52:48Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.