Malicious GenAI Chrome Extensions: Unpacking Data Exfiltration and Malicious Behaviours

2025-12-10

AI Summary

To address the proliferation of malicious Chrome extensions masquerading as generative AI (GenAI) tools in the Chrome Web Store, this paper constructs the first large-scale, AI-themed extension dataset and proposes a multi-signal collaborative detection framework integrating manifest-based static analysis, domain reputation assessment, and dynamic network behavior monitoring. Through manual verification and reverse engineering, we identify 341 malicious extensions, including 29 explicitly associated with GenAI; among these, 154 are newly discovered malicious GenAI extensions. Our analysis reveals prevalent attack patterns—including sensitive data exfiltration, traffic hijacking, and impersonation of mainstream AI models—and provides empirical evidence that advanced threats such as Adversary-in-the-Browser have been operationally deployed at scale within the GenAI ecosystem. This work establishes a foundational dataset and detection methodology to support AI security governance and threat intelligence for browser-based AI applications.

Technology Category

• Application Domains: Misinformation & Fake News
• Computer Vision: Adversarial Attacks & Robustness
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The rapid proliferation of AI and GenAI tools has extended to the Chrome Web Store. Cybercriminals are exploiting this trend, deploying malicious Chrome extensions posing as AI tools or impersonating popular GenAI models to target users. These extensions often appear legitimate while secretly exfiltrating sensitive data or redirecting users web traffic to attacker-controlled domains. To examine the impact of this trend on the browser extension ecosystem, we curated a dataset of 5,551 AI-themed extensions released over a nine-month period to the Chrome Web Store. Using a multi-signal detection methodology that combines manifest analysis, domain reputation, and runtime network behavior, supplemented with human review, we identified 154 previously undetected malicious Chrome extensions. Together with extensions known from public threat research disclosures, this resulted in a final set of 341 malicious extensions for analysis. Of these, 29 were GenAI-related, forming the focus of our in-depth analysis and disclosure. We deconstruct representative GenAI cases, including Supersonic AI, DeepSeek AI | Free AI Assistant, and Perplexity Search, to illustrate attacker techniques such as Adversary-in-the-Browser, impersonation, bait-and-switch updates, query hijacking, and redirection. Our findings show that threat actors are leveraging GenAI trends and exploiting browser extension APIs and settings for malicious purposes. This demonstrates that the browser extension threat landscape is directly evolving alongside the rapid adoption of GenAI technologies.

Problem

• Detect malicious Chrome extensions exploiting GenAI trends
• Analyze data exfiltration and redirection techniques in extensions
• Assess evolving threats in browser ecosystem from GenAI adoption

Innovation

• Multi-signal detection combining manifest and network analysis
• Dataset of 5,551 AI-themed extensions over nine months
• Deconstruction of GenAI cases to illustrate attacker techniques