Client-Side Zero-Shot LLM Inference for Comprehensive In-Browser URL Analysis

• URL: http://arxiv.org/abs/2506.03656v1
• Date: Wed, 04 Jun 2025 07:47:23 GMT
• Title: Client-Side Zero-Shot LLM Inference for Comprehensive In-Browser URL Analysis
• Authors: Avihay Cohen,
• Abstract summary: Malicious websites and phishing URLs pose an ever-increasing cybersecurity risk.<n>Traditional detection approaches rely on machine learning.<n>We propose a novel client-side framework for comprehensive URL analysis.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Malicious websites and phishing URLs pose an ever-increasing cybersecurity risk, with phishing attacks growing by 40% in a single year. Traditional detection approaches rely on machine learning classifiers or rule-based scanners operating in the cloud, but these face significant challenges in generalization, privacy, and evasion by sophisticated threats. In this paper, we propose a novel client-side framework for comprehensive URL analysis that leverages zero-shot inference by a local large language model (LLM) running entirely in-browser. Our system uses a compact LLM (e.g., 3B/8B parameters) via WebLLM to perform reasoning over rich context collected from the target webpage, including static code analysis (JavaScript abstract syntax trees, structure, and code patterns), dynamic sandbox execution results (DOM changes, API calls, and network requests),and visible content. We detail the architecture and methodology of the system, which combines a real browser sandbox (using iframes) resistant to common anti-analysis techniques, with an LLM-based analyzer that assesses potential vulnerabilities and malicious behaviors without any task-specific training (zero-shot). The LLM aggregates evidence from multiple sources (code, execution trace, page content) to classify the URL as benign or malicious and to provide an explanation of the threats or security issues identified. We evaluate our approach on a diverse set of benign and malicious URLs, demonstrating that even a compact client-side model can achieve high detection accuracy and insightful explanations comparable to cloud-based solutions, while operating privately on end-user devices. The results show that client-side LLM inference is a feasible and effective solution to web threat analysis, eliminating the need to send potentially sensitive data to cloud services.

Related papers

• Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems [18.039444159491733]
  Large Language Models (LLMs) deployed in enterprise settings face novel security challenges.<n>One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually extract confidential data.<n>We present a comprehensive study of multi-stage prompt inference attacks in an enterprise LLM context.
  arXiv  Detail & Related papers  (2025-07-21T13:38:12Z)
• The Hidden Dangers of Browsing AI Agents [0.0]
  This paper presents a comprehensive security evaluation of such agents, focusing on systemic vulnerabilities across multiple architectural layers.<n>Our work outlines the first end-to-end threat model for browsing agents and provides actionable guidance for securing their deployment in real-world environments.
  arXiv  Detail & Related papers  (2025-05-19T13:10:29Z)
• AGENTFUZZER: Generic Black-Box Fuzzing for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentXploit, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentXploit on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation [88.78166077081912]
  We introduce a multimodal unlearning benchmark, UnLOK-VQA, and an attack-and-defense framework to evaluate methods for deleting specific multimodal knowledge from MLLMs.<n>Our results show multimodal attacks outperform text- or image-only ones, and that the most effective defense removes answer information from internal model states.
  arXiv  Detail & Related papers  (2025-05-01T01:54:00Z)
• How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities [62.474732677086855]
  Large language model (LLM) routing has emerged as a crucial strategy for balancing computational costs with performance.<n>We propose the DSC benchmark: Diverse, Simple, and Categorized, an evaluation framework that categorizes router performance across a broad spectrum of query types.
  arXiv  Detail & Related papers  (2025-03-20T19:52:30Z)
• Efficient Phishing URL Detection Using Graph-based Machine Learning and Loopy Belief Propagation [12.89058029173131]
  We propose a graph-based machine learning model for phishing URL detection.<n>We integrate URL structure and network-level features such as IP addresses and authoritative name servers.<n>Experiments on real-world datasets demonstrate our model's effectiveness by achieving F1 score of up to 98.77%.
  arXiv  Detail & Related papers  (2025-01-12T19:49:00Z)
• "Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models [74.05368440735468]
  Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) In this paper, we demonstrate a security threat where adversaries can exploit the openness of these knowledge bases.
  arXiv  Detail & Related papers  (2024-06-26T05:36:23Z)
• Dissecting Adversarial Robustness of Multimodal LM Agents [70.2077308846307]
  We manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena.<n>We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search.<n>We also use ARE to rigorously evaluate how the robustness changes as new components are added.
  arXiv  Detail & Related papers  (2024-06-18T17:32:48Z)
• PhishGuard: A Convolutional Neural Network Based Model for Detecting Phishing URLs with Explainability Analysis [1.102674168371806]
  Phishing URL identification is the best way to address the problem. Various machine learning and deep learning methods have been proposed to automate the detection of phishing URLs. We propose a 1D Convolutional Neural Network (CNN) and trained the model with extensive features and a substantial amount of data.
  arXiv  Detail & Related papers  (2024-04-27T17:13:49Z)
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection [64.67495502772866]
  Large Language Models (LLMs) are increasingly being integrated into various applications. We show how attackers can override original instructions and employed controls using Prompt Injection attacks. We derive a comprehensive taxonomy from a computer security perspective to systematically investigate impacts and vulnerabilities.
  arXiv  Detail & Related papers  (2023-02-23T17:14:38Z)
• CrowdGuard: Federated Backdoor Detection in Federated Learning [39.58317527488534]
  This paper presents a novel defense mechanism, CrowdGuard, that effectively mitigates backdoor attacks in Federated Learning. CrowdGuard employs a server-located stacked clustering scheme to enhance its resilience to rogue client feedback. The evaluation results demonstrate that CrowdGuard achieves a 100% True-Positive-Rate and True-Negative-Rate across various scenarios.
  arXiv  Detail & Related papers  (2022-10-14T11:27:49Z)
• An Adversarial Attack Analysis on Malicious Advertisement URL Detection Framework [22.259444589459513]
  Malicious advertisement URLs pose a security risk since they are the source of cyber-attacks. Existing malicious URL detection techniques are limited and to handle unseen features as well as generalize to test data. In this study, we extract a novel set of lexical and web-scrapped features and employ machine learning technique to set up system for fraudulent advertisement URLs detection.
  arXiv  Detail & Related papers  (2022-04-27T20:06:22Z)

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.