Skip to content
Semantic vs. Token-Based LLM Injections
blog.sentry.security | blog | #ai-security | #prompt-injection | #llm | #owasp | #tokenization | #adversarial-ml
Summary
Contrasting two LLM injection classes: semantic attacks use natural language to override instructions; token-based attacks exploit tokenizer quirks like reserved delimiters and adversarial suffixes.
- Published
- Collected