Towards LLM-Enhanced Android Taint Analysis

• URL: http://arxiv.org/abs/2608.24269v1
• Date: Tue, 25 Aug 2026 08:57:13 GMT
• Title: Towards LLM-Enhanced Android Taint Analysis
• Abstract summary: We investigate whether off-the-shelf Large Language Models can effectively reason about taint flows in Android apps.<n>Our approach relies on an agentic interaction strategy, enabling the LLM to iteratively explore code and reason about data flows.<n>Preliminary findings suggest that LLM reasoning may effectively complement traditional static taint analysis.
• Score: 7.264089733230453
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Taint analysis is a fundamental technique for detecting sensitive data leaks in Android apps. However, traditional static tools, such as FlowDroid, still face well-known challenges due to the complexity of accurately modeling the Android framework. In this paper, we investigate whether off-the-shelf Large Language Models (LLMs) can effectively reason about taint flows in Android apps. Our preliminary approach relies on an agentic interaction strategy, enabling the LLM to iteratively explore code and reason about data flows. We conduct an initial evaluation on the DroidBench benchmark against FlowDroid, where our approach outperforms the baseline: Gemini-3 Flash achieves an F1-score of 0.96, compared to 0.55 for FlowDroid. In particular, we observe improvements in challenging categories such as inter-component communication (0.95 vs. 0.17), implicit flows (0.94 vs. 0.00), and reflection (1.00 vs. 0.50), where FlowDroid typically struggles. On a small set of real-world apps, the LLM-based approach also identifies additional potential data leaks not reported by FlowDroid. These preliminary findings suggest that LLM reasoning may effectively complement traditional static taint analysis, motivating future research on hybrid LLM-enhanced taint analysis pipelines.

Related papers

• OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis [98.43366988856592]
  We present OpenMobile, an open-source framework that synthesizes high-quality task instructions and agent trajectories.<n>Agents trained on our data achieve competitive results across three dynamic mobile agent benchmarks.
  arXiv  Detail & Related papers  (2026-04-16T14:53:08Z)
• Benchmark Leakage Trap: Can We Trust LLM-based Recommendation? [9.574427977779235]
  This paper identifies and investigates a previously overlooked issue: benchmark data leakage in LLM-based recommendation.<n>Data leakage acts as a critical, previously unaccounted-for factor in LLM-based recommendation, which could impact the true model performance.
  arXiv  Detail & Related papers  (2026-02-14T06:34:19Z)
• AndroByte: LLM-Driven Privacy Analysis through Bytecode Summarization and Dynamic Dataflow Call Graph Generation [0.0]
  AndroByte is an AI-driven privacy analysis tool for Android apps.<n>It generates accurate and explainable dataflow call graphs from static code analysis.<n>AndrosByte achieves a significant Fbeta-Score of 89% in generating dynamic dataflow call graphs on the fly.
  arXiv  Detail & Related papers  (2025-10-16T20:10:20Z)
• When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs [55.20230501807337]
  We present the first systematic evaluation of 5 methods for improving prompt robustness within a unified experimental framework.<n>We benchmark these techniques on 8 models from Llama, Qwen and Gemma families across 52 tasks from Natural Instructions dataset.
  arXiv  Detail & Related papers  (2025-08-15T10:32:50Z)
• MalFlows: Context-aware Fusion of Heterogeneous Flow Semantics for Android Malware Detection [18.782868339492243]
  MalFlows is a novel technique that achieves context-aware fusion of heterogeneous flow semantics for Android malware detection.<n>Flow2vec is a context-aware HIN embedding technique that distinguishes the semantics of HIN entities as needed based on contextual constraints.<n>We evaluate MalFlows on a large-scale dataset comprising over 20 million flow instances extracted from more than 31,000 real-world apps.
  arXiv  Detail & Related papers  (2025-08-05T15:54:52Z)
• Enhancing Android Malware Detection with Retrieval-Augmented Generation [1.413488665073795]
  In this work, we focus on a Machine Learning-based method utilizing static features.<n>To mitigate hallucinations, which are a known vulnerability of LLM, we integrated Retrieval-Augmented Generation.<n>Using carefully designed prompts, we guide the LLM to produce coherent function summaries, which are then analyzed using a transformer-based model.
  arXiv  Detail & Related papers  (2025-06-28T04:36:31Z)
• DroidTTP: Mapping Android Applications with TTP for Cyber Threat Intelligence [13.958337678497163]
  DroidTTP is a framework mapping Android malware behaviors to Tactics, Techniques, and Procedures (TTPs)<n>Our dataset explicitly links MITRE TTPs to Android applications.<n>We developed an automated solution leveraging the Problem Transformation Approach (PTA) and Large Language Models (LLMs)
  arXiv  Detail & Related papers  (2025-03-20T05:38:24Z)
• 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)
• LLM Robustness Against Misinformation in Biomedical Question Answering [50.98256373698759]
  The retrieval-augmented generation (RAG) approach is used to reduce the confabulation of large language models (LLMs) for question answering. We evaluate the effectiveness and robustness of four LLMs against misinformation in answering biomedical questions.
  arXiv  Detail & Related papers  (2024-10-27T16:23:26Z)
• LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond [135.8013388183257]
  We propose a new protocol for inconsistency detection benchmark creation and implement it in a 10-domain benchmark called SummEdits. Most LLMs struggle on SummEdits, with performance close to random chance. The best-performing model, GPT-4, is still 8% below estimated human performance.
  arXiv  Detail & Related papers  (2023-05-23T21:50:06Z)
• Re-Evaluating LiDAR Scene Flow for Autonomous Driving [80.37947791534985]
  Popular benchmarks for self-supervised LiDAR scene flow have unrealistic rates of dynamic motion, unrealistic correspondences, and unrealistic sampling patterns. We evaluate a suite of top methods on a suite of real-world datasets. We show that despite the emphasis placed on learning, most performance gains are caused by pre- and post-processing steps.
  arXiv  Detail & Related papers  (2023-04-04T22:45:50Z)

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.