Codetta: High-Capacity, Keyless, and Undetectable Multi-Agent Collusion

arXiv:2609.28900 · cs.CR, cs.MA · Submitted 2026-09-24 · Read on arXiv

cs.CR, cs.MA

Submitted: 2026-09-24

Updated: 2026-09-25

Terminology

• Decode — 18× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Multi-Agent System — 6× in this paper · explained in 6 episodes
• Trace — 5× in this paper · explained in 2 episodes
• Speculative Decoding — 4× in this paper · explained in 2 episodes
• AI Agents — 3× in this paper · explained in 2 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Calibration — 2× in this paper · explained in 7 episodes
• Hamming Distance — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Module Learning With Errors — 2× in this paper
• Redundancy — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Security and Privacy — 2× in this paper
• Ablation Studies — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Capture The Flag — 1× in this paper
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Information Asymmetry — 1× in this paper · explained in 2 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Research Review — 1× in this paper · explained in 6 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
• Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
• Accelerating Large Language Model Decoding with Speculative Sampling
• LlamaFirewall: An open source guardrail system for building secure AI agents
• The Llama 3 Herd of Models
• Sionna: An Open-Source Library for Next-Generation Physical Layer Research
• Ministral 3
• Steganography Without Modification: Hidden Communication via LLM Seeds
• Preventing Language Models From Hiding Their Reasoning
• When Autonomy Goes Rogue: Preparing for Risks of Multi-Agent Collusion in Social Systems
• Undetectable Conversations Between AI Agents via Pseudorandom Noise-Resilient Key Exchange
• Qwen2.5 Technical Report
• Excuse me, sir? Your language model is leaking (information)
• Instruction-Following Evaluation for Large Language Models
• Conceptual Steganography

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs