Deep(er) Web Indexing with LLMs

Abstract

AbstractThe “Deep Web” contains, among other data, sensitive information that is left unsecured and publicly available but not indexed and thus impossible to locate by search engines. Using search-augmented language models can potentially make the deep web shallower and more searchable, posing a concern for cyber defense, particularly in countries with linguistic specifics. Mitigation strategies include red-teaming of LLM-based search engines, end-to-end encryption, or modifying terms used in critical cyber-physical systems to make resources harder to find. However, these approaches may have limitations and cause potential disruptions to user workflows.