LLM-Driven Feature-Level Adversarial Attacks on Android Malware Detectors

• URL: http://arxiv.org/abs/2512.21404v1
• Date: Wed, 24 Dec 2025 19:56:06 GMT
• Title: LLM-Driven Feature-Level Adversarial Attacks on Android Malware Detectors
• Authors: Tianwei Lan, Farid Naït-Abdesselam,
• Abstract summary: LAMLAD is a novel adversarial attack framework for Android malware detection.<n>It exploits the generative and reasoning capabilities of large language models.<n>LAMLAD achieves an attack success rate (ASR) of up to 97%, requiring on average only three attempts per adversarial sample.
• Score: 3.4703956485057152
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid growth in both the scale and complexity of Android malware has driven the widespread adoption of machine learning (ML) techniques for scalable and accurate malware detection. Despite their effectiveness, these models remain vulnerable to adversarial attacks that introduce carefully crafted feature-level perturbations to evade detection while preserving malicious functionality. In this paper, we present LAMLAD, a novel adversarial attack framework that exploits the generative and reasoning capabilities of large language models (LLMs) to bypass ML-based Android malware classifiers. LAMLAD employs a dual-agent architecture composed of an LLM manipulator, which generates realistic and functionality-preserving feature perturbations, and an LLM analyzer, which guides the perturbation process toward successful evasion. To improve efficiency and contextual awareness, LAMLAD integrates retrieval-augmented generation (RAG) into the LLM pipeline. Focusing on Drebin-style feature representations, LAMLAD enables stealthy and high-confidence attacks against widely deployed Android malware detection systems. We evaluate LAMLAD against three representative ML-based Android malware detectors and compare its performance with two state-of-the-art adversarial attack methods. Experimental results demonstrate that LAMLAD achieves an attack success rate (ASR) of up to 97%, requiring on average only three attempts per adversarial sample, highlighting its effectiveness, efficiency, and adaptability in practical adversarial settings. Furthermore, we propose an adversarial training-based defense strategy that reduces the ASR by more than 30% on average, significantly enhancing model robustness against LAMLAD-style attacks.

Related papers

• Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities [76.9327488986162]
  Existing attacks against multimodal language models (MLLMs) primarily communicate instructions through text accompanied by adversarial images.<n>We exploit the capabilities of MLLMs to interpret non-textual instructions, specifically, adversarial images or audio generated by our novel method, Con Instruction.<n>Our method achieves the highest attack success rates, reaching 81.3% and 86.6% on LLaVA-v1.5 (13B)
  arXiv  Detail & Related papers  (2025-05-31T13:11:14Z)
• LAMD: Context-driven Android Malware Detection and Classification with LLMs [8.582859303611881]
  Large Language Models (LLMs) offer a promising alternative with their zero-shot inference and reasoning capabilities.<n>We propose LAMD, a practical context-driven framework to enable LLM-based Android malware detection.
  arXiv  Detail & Related papers  (2025-02-18T17:01:37Z)
• Adversarial Reasoning at Jailbreaking Time [49.70772424278124]
  Large language models (LLMs) are becoming more capable and widespread.<n>Recent advances in standardizing, measuring, and scaling test-time compute suggest new methodologies for optimizing models to achieve high performance on hard tasks.<n>In this paper, we apply these advances to the task of model jailbreaking: eliciting harmful responses from aligned LLMs.
  arXiv  Detail & Related papers  (2025-02-03T18:59:01Z)
• LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models [59.29840790102413]
  Existing jailbreak attacks are primarily based on opaque optimization techniques and gradient search methods.<n>We propose LLM-Virus, a jailbreak attack method based on evolutionary algorithm, termed evolutionary jailbreak.<n>Our results show that LLM-Virus achieves competitive or even superior performance compared to existing attack methods.
  arXiv  Detail & Related papers  (2024-12-28T07:48:57Z)
• Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models [17.663550432103534]
  Multimodal Large Language Models (MLLMs) extend the capacity of LLMs to understand multimodal information comprehensively. These models are susceptible to jailbreak attacks, where malicious users can break the safety alignment of the target model and generate misleading and harmful answers. We propose Cross-modality Information DEtectoR (CIDER), a plug-and-play jailbreaking detector designed to identify maliciously perturbed image inputs.
  arXiv  Detail & Related papers  (2024-07-31T15:02:46Z)
• AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models [95.09157454599605]
  Large Language Models (LLMs) are becoming increasingly powerful, but they still exhibit significant but subtle weaknesses.<n>Traditional benchmarking approaches cannot thoroughly pinpoint specific model deficiencies.<n>We introduce a unified framework, AutoDetect, to automatically expose weaknesses in LLMs across various tasks.
  arXiv  Detail & Related papers  (2024-06-24T15:16:45Z)
• Defending Large Language Models Against Attacks With Residual Stream Activation Analysis [0.0]
  Large Language Models (LLMs) are vulnerable to adversarial threats.<n>This paper presents an innovative defensive strategy, given white box access to an LLM.<n>We apply a novel methodology for analyzing distinctive activation patterns in the residual streams for attack prompt classification.
  arXiv  Detail & Related papers  (2024-06-05T13:06:33Z)
• Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
  Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses. C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
  arXiv  Detail & Related papers  (2024-05-24T14:20:09Z)
• Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes [61.916827858666906]
  Large Language Models (LLMs) are becoming a prominent generative AI tool, where the user enters a query and the LLM generates an answer. To reduce harm and misuse, efforts have been made to align these LLMs to human values using advanced training techniques such as Reinforcement Learning from Human Feedback. Recent studies have highlighted the vulnerability of LLMs to adversarial jailbreak attempts aiming at subverting the embedded safety guardrails. This paper proposes a method called Gradient Cuff to detect jailbreak attempts.
  arXiv  Detail & Related papers  (2024-03-01T03:29:54Z)
• On the Vulnerability of LLM/VLM-Controlled Robotics [54.57914943017522]
  We highlight vulnerabilities in robotic systems integrating large language models (LLMs) and vision-language models (VLMs) due to input modality sensitivities.<n>Our results show that simple input perturbations reduce task execution success rates by 22.2% and 14.6% in two representative LLM/VLM-controlled robotic systems.
  arXiv  Detail & Related papers  (2024-02-15T22:01:45Z)
• MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks [18.016148305499865]
  MalPurifier is a novel adversarial purification framework specifically engineered for Android malware detection.<n>Experiments on two large-scale datasets demonstrate that MalPurifier significantly outperforms state-of-the-art defenses.<n>As a lightweight, model-agnostic, and plug-and-play module, MalPurifier offers a practical and effective solution to bolster the security of ML-based Android malware detectors.
  arXiv  Detail & Related papers  (2023-12-11T14:48:43Z)
• PAD: Towards Principled Adversarial Malware Detection Against Evasion Attacks [17.783849474913726]
  We propose a new adversarial training framework, termed Principled Adversarial Malware Detection (PAD) PAD lays on a learnable convex measurement that quantifies distribution-wise discrete perturbations to protect malware detectors from adversaries. PAD can harden ML-based malware detection against 27 evasion attacks with detection accuracies greater than 83.45%. It matches or outperforms many anti-malware scanners in VirusTotal against realistic adversarial malware.
  arXiv  Detail & Related papers  (2023-02-22T12:24:49Z)

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.