An LLM-based agentic eavesdropper recovers private information from semantic communication signals with over 75% success at SNR >=5 dB without needing wiretap channel state information.
Towards secure semantic communications in the presence of intelligent eaves- droppers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Agentic AI enables coverless semantic steganography without private keys or cover images, delivering higher capacity and security than prior schemes in semantic communication.
citing papers explorer
-
When Eavesdroppers Reason: Agentic Eavesdropping Attacks on Semantic Communication
An LLM-based agentic eavesdropper recovers private information from semantic communication signals with over 75% success at SNR >=5 dB without needing wiretap channel state information.
-
Secure Intellicise Wireless Network: Agentic AI for Coverless Semantic Steganography Communication
Agentic AI enables coverless semantic steganography without private keys or cover images, delivering higher capacity and security than prior schemes in semantic communication.