LLM Covert Channels: How AI Agents Exfiltrate Data in Plain Sight

An agent summarizes a document. The summary looks correct. DLP approves it. No alert fires. But 64 bytes of the user's session token are now encoded in the pattern of synonym choices the model made. Invisible to every tool in the pipeline, readable by any system that knows the key. DLP tools scan for recognizable patterns in transmitted text. An... Weiterlesen