BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912729050120192 |
|---|---|
| author | Zhang, Kaiyuan Tenenholtz, Mark Polley, Kyle Ma, Jerry Yarats, Denis Li, Ninghui |
| author_facet | Zhang, Kaiyuan Tenenholtz, Mark Polley, Kyle Ma, Jerry Yarats, Denis Li, Ninghui |
| contents | The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web agents, yet the resulting impact within real-world environments remains insufficiently understood.
In this work, we examine the landscape of prompt injection attacks and synthesize a benchmark of attacks embedded in realistic HTML payloads. Our benchmark goes beyond prior work by emphasizing injections that can influence real-world actions rather than mere text outputs, and by presenting attack payloads with complexity and distractor frequency similar to what real-world agents encounter. We leverage this benchmark to conduct a comprehensive empirical evaluation of existing defenses, assessing their effectiveness across a suite of frontier AI models. We propose a multi-layered defense strategy comprising both architectural and model-based defenses to protect against evolving prompt injection attacks. Our work offers a blueprint for designing practical, secure web agents through a defense-in-depth approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_20597 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents Zhang, Kaiyuan Tenenholtz, Mark Polley, Kyle Ma, Jerry Yarats, Denis Li, Ninghui Machine Learning Artificial Intelligence Cryptography and Security The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web agents, yet the resulting impact within real-world environments remains insufficiently understood. In this work, we examine the landscape of prompt injection attacks and synthesize a benchmark of attacks embedded in realistic HTML payloads. Our benchmark goes beyond prior work by emphasizing injections that can influence real-world actions rather than mere text outputs, and by presenting attack payloads with complexity and distractor frequency similar to what real-world agents encounter. We leverage this benchmark to conduct a comprehensive empirical evaluation of existing defenses, assessing their effectiveness across a suite of frontier AI models. We propose a multi-layered defense strategy comprising both architectural and model-based defenses to protect against evolving prompt injection attacks. Our work offers a blueprint for designing practical, secure web agents through a defense-in-depth approach. |
| title | BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents |
| topic | Machine Learning Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2511.20597 |