Why Prompt Filters Fail Against LLM Attacks

Podcast: Pop Goes the Stack · F5

Opublikowano: 2026-04-14

Prompt injection has been the headline security problem for the last year, but have we been guarding the wrong layer? Lori MacVittie is joined by cohost Joel Moses and architect Elijah Zupancic to break down why many “prompt filters” miss the real execution surface: models don’t process words, they process tokens, and attackers are increasingly targeting the tokenizer to bypass defenses. Using the research behind Adversarial Tokenization and TokenBreak, they explain how the same text can be segmented into different token paths, changing what the model actually “sees” and how it behaves. That creates a...