Early Signs of Steganographic Capabilities in Frontier LLMs
Monitoring Large Language Model (LLM) outputs is crucial for mitigating risks from misuse and misalignment. However, LLMs could evade monitoring through steganography: Encoding hidden information within seemingly benign generations. In this paper, we evaluate the steganography capabilities in frontier LLMs to better understand the risk they pose. We focus on two types of steganography: passing encoded messages and performing encoded reasoning. We find that current models are unable to encode short messages in their outputs without a monitor noticing under standard affordances. They can succeed, however, if given additional affordances such as using an unmonitored scratchpad and coordinating on what encoding scheme to use. We additionally find early signs that models can perform basic encoded reasoning in a simple state-tracking problem. This includes some ability to reason with their own and pre-defined schemes, including encoding schemes such as Hexadecimal. Despite this, they can rarely hide reasoning subtly within a cover task to fool a monitor. Overall, our results indicate that current LLMs exhibit nascent steganographic capabilities. While these capabilities are likely insufficient to bypass well-designed monitors at present, this could change in the future.
Code (1)
Tasks
Large Language ModelMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Secret Collusion among Generative AI Agents: Multi-Agent Deception via Steganography
Recent capability increases in large language models (LLMs) open up applications in which groups of communicating generative AI agents solve joint tasks. This poses privacy and security challenges concerning the unauthor…
Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs
The rapid proliferation of frontier model agents promises significant societal advances but also raises concerns about systemic risks arising from unsafe interactions. Collusion to the disadvantage of others has been ide…
In-Context Reinforcement Learningreinforcement-learningReinforcement LearningA Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms. Yet principled methods to detect and quantify such behaviours are la…
An Early Warning of Emerging Biosecurity Risks in Frontier LLMs
Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the biological risks of frontier models, we…
The Steganographic Potentials of Language Models
The potential for large language models (LLMs) to hide messages within plain text (steganography) poses a challenge to detection and thwarting of unaligned AI agents, and undermines faithfulness of LLMs reasoning. We exp…
Reinforcement Learning (RL)