SAFuzz: Semantic-Guided Adaptive Fuzzing for LLM-Generated Code

• URL: http://arxiv.org/abs/2602.11209v1
• Date: Wed, 11 Feb 2026 02:19:50 GMT
• Title: SAFuzz: Semantic-Guided Adaptive Fuzzing for LLM-Generated Code
• Abstract summary: SAFuzz integrates prompt-based behavioral diversification, harness generation with problem-specific oracles, and an LLM-based predictor to enable adaptive resource allocation and dynamic early stopping.<n>We improve vulnerability discrimination precision from 77.9% to 85.7% and achieve a 1.71x reduction in time cost compared to SOTA GreenFuzz.
• Score: 15.89862532277037
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While AI-coding assistants accelerate software development, current testing frameworks struggle to keep pace with the resulting volume of AI-generated code. Traditional fuzzing techniques often allocate resources uniformly and lack semantic awareness of algorithmic vulnerability patterns, leading to inefficient resource usage and missed vulnerabilities. To address these limitations, we present a hybrid testing framework that leverages LLM-guided adaptive fuzzing to detect algorithmic vulnerabilities efficiently. Our system SAFuzz integrates prompt-based behavioral diversification, harness generation with problem-specific oracles, and an LLM-based predictor to enable adaptive resource allocation and dynamic early stopping. Evaluating SAFuzz on CSES algorithmic problems, we improve vulnerability discrimination precision from 77.9% to 85.7% and achieve a 1.71x reduction in time cost compared to SOTA GreenFuzz while maintaining comparable recall. We further observe that combining our approach with existing unit test generation methods yields complementary gains, increasing the bug detection recall from 67.3% to 79.5%.

Related papers

• Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization [51.11398557420066]
  We introduce Metis, a framework that reformulates jailbreaking as inference-time policy optimization.<n>Metis achieves the strongest average Attack Success Rate (ASR) among compared methods at 89.2%.<n>By replacing redundant exploration with directed optimization, Metis reduces token costs by an average of 8.2x and up to 11.4x.
  arXiv  Detail & Related papers  (2026-05-11T06:45:00Z)
• Synergistic Directed Execution and LLM-Driven Analysis for Zero-Day AI-Generated Malware Detection [0.12891210250935145]
  Weaponization of LLMs for automated malware generation poses an existential threat to conventional detection paradigms.<n>This paper introduces a novel hybrid analysis framework that combines emphconcolic execution with emphdeep-learning-based vulnerability classification.<n>A benchmark comprising 2,500 LLM-synthesized samples achieves 98.7% accuracy on conventional malware and 97.5% accuracy on AI-generated threats.
  arXiv  Detail & Related papers  (2026-03-10T00:25:41Z)
• ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference [60.958331943869126]
  ODAR-Expert is an adaptive routing framework that optimize the accuracy-efficiency trade-off via principled resource allocation.<n>We show strong and consistent gains, including 98.2% accuracy on MATH and 54.8% on Humanity's Last Exam.
  arXiv  Detail & Related papers  (2026-02-27T05:22:01Z)
• VulSolver: Vulnerability Detection via LLM-Driven Constraint Solving [23.259666449166456]
  Traditional vulnerability detection methods rely heavily on predefined rule matching.<n>We propose a constraint-solving approach powered by large language models (LLMs)<n>We assess VULSOLVER on the Benchmark, achieving 97.85% accuracy, 97.97% F1-score, and 100% recall.
  arXiv  Detail & Related papers  (2025-08-31T14:49:48Z)
• Enhancing Software Vulnerability Detection Through Adaptive Test Input Generation Using Genetic Algorithm [2.02449352795006]
  This study introduces a genetic algorithm-based method for test input generation.<n>It integrates genetic operators and adaptive learning to enhance software vulnerability detection.<n>Results highlight the method's capacity to detect deeper and more complex vulnerabilities.
  arXiv  Detail & Related papers  (2025-08-08T01:03:22Z)
• Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language Models [87.66870367661342]
  Large language models (LLMs) are used in AI applications in healthcare.<n>Red-teaming framework that continuously stress-test LLMs can reveal significant weaknesses in four safety-critical domains.<n>A suite of adversarial agents is applied to autonomously mutate test cases, identify/evolve unsafe-triggering strategies, and evaluate responses.<n>Our framework delivers an evolvable, scalable, and reliable safeguard for the next generation of medical AI.
  arXiv  Detail & Related papers  (2025-07-30T08:44:22Z)
• LLAMA: Multi-Feedback Smart Contract Fuzzing Framework with LLM-Guided Seed Generation [56.84049855266145]
  We propose a Multi-feedback Smart Contract Fuzzing framework (LLAMA) that integrates evolutionary mutation strategies, and hybrid testing techniques.<n>LLAMA achieves 91% instruction coverage and 90% branch coverage, while detecting 132 out of 148 known vulnerabilities.<n>These results highlight LLAMA's effectiveness, adaptability, and practicality in real-world smart contract security testing scenarios.
  arXiv  Detail & Related papers  (2025-07-16T09:46:58Z)
• A Mixture of Linear Corrections Generates Secure Code [20.94236753015922]
  Large language models (LLMs) have become proficient at sophisticated code-generation tasks, yet remain ineffective at reliably detecting or avoiding code vulnerabilities.<n>We find that current LLMs encode precise internal representations that distinguish vulnerable from secure code.<n>We develop an inference-time steering technique that subtly modulates the model's token-generation probabilities through a mixture of corrections.
  arXiv  Detail & Related papers  (2025-07-13T06:27:33Z)
• Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders [50.52694757593443]
  Existing SAE training algorithms often lack rigorous mathematical guarantees and suffer from practical limitations.<n>We first propose a novel statistical framework for the feature recovery problem, which includes a new notion of feature identifiability.<n>We introduce a new SAE training algorithm based on bias adaptation'', a technique that adaptively adjusts neural network bias parameters to ensure appropriate activation sparsity.
  arXiv  Detail & Related papers  (2025-06-16T20:58:05Z)
• Breaking the Loop: Detecting and Mitigating Denial-of-Service Vulnerabilities in Large Language Models [4.046135652393372]
  Large Language Models (LLMs) have significantly advanced text understanding and generation, becoming integral to applications across education, software development, healthcare, entertainment, and legal services.<n>Recurrent generation, where models repeatedly produce similar or identical outputs, causes increased latency and potential Denial-of-Service (DoS) vulnerabilities.<n>We propose RecurrentGenerator, a black-box evolutionary algorithm that efficiently identifies recurrent generation scenarios in prominent LLMs like LLama-3 and GPT-4o.
  arXiv  Detail & Related papers  (2025-03-01T09:32:17Z)
• Adaptive Distraction: Probing LLM Contextual Robustness with Automated Tree Search [76.54475437069395]
  Large Language Models (LLMs) often struggle to maintain their original performance when faced with semantically coherent but task-irrelevant contextual information.<n>We propose a dynamic distraction generation framework based on tree search, where the generation process is guided by model behavior.
  arXiv  Detail & Related papers  (2025-02-03T18:43:36Z)
• StagedVulBERT: Multi-Granular Vulnerability Detection with a Novel Pre-trained Code Model [13.67394549308693]
  This study introduces StagedVulBERT, a novel vulnerability detection framework. CodeBERT-HLS component is designed to capture semantics at both the token and statement levels simultaneously. In coarse-grained vulnerability detection, StagedVulBERT achieves an F1 score of 92.26%, marking a 6.58% improvement over the best-performing methods.
  arXiv  Detail & Related papers  (2024-10-08T07:46:35Z)
• 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)
• Anomaly Detection Based on Selection and Weighting in Latent Space [73.01328671569759]
  We propose a novel selection-and-weighting-based anomaly detection framework called SWAD. Experiments on both benchmark and real-world datasets have shown the effectiveness and superiority of SWAD.
  arXiv  Detail & Related papers  (2021-03-08T10:56:38Z)

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.