As large language models (LLMs) become more and more skilled at writing human-like text, the ability to detect what they generate is critical. This session explores an attack vector, homoglyph-based attacks, that effectively bypasses state-of-the-art LLM detectors.

We'll begin by explaining the idea behind homoglyphs, characters that look similar but are encoded differently. You'll learn how these can be used to manipulate tokenization and evade detection systems. We'll cover the mechanisms of how homoglyphs alter text representation, discuss their impact on existing LLM detectors, and present a comprehensive evaluation of their effectiveness against various detection methods.

Join us for an engaging exploration of this emerging threat and to stay ahead of evolving evasion techniques!