RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?

MATS 学员:

Rohan Gupta

作者:

Rohan Gupta, Erik Jenner

引用次数

9 Citations

摘要:

Latent-space monitors aim to detect undesirable behaviours in Large Language Models by leveraging their internal representations rather than relying solely on black-box outputs. These methods have shown promise in identifying behaviours such as deception and unsafe completions. However, these monitors may themselves become training signals, for example, by using problematic samples found in deployment to retrain models. This raises an important question: can models learn to evade such monitors? To evaluate this capability, we introduce RL-Obfuscation, in which LLMs are finetuned via reinforcement learning to evade latent-space monitors while maintaining their blackbox behaviour. We apply RL-Obfuscation to Language Models ranging from 7B to 14B parameters and evaluate their Evasion Success Rate against a suite of monitors. We find that token-level monitors are highly vulnerable to this attack while more holistic monitors, such as max-pooling or attention-based probes, remain robust. Moreover, for these vulnerable monitors, models trained to evade a single static monitor can generalise to evade other unseen monitors. We also find that the models can be trained to conditionally bypass latent-space monitors on only certain inputs. Finally, we study how the models bypass these monitors and find that the model can learn to repurpose tokens to have different internal representations.

近期研究

非大国冲突与 AI 风险

作者:

Kristina Kempkey

日期:

八月 26, 2026

引用次数:

合成角色预训练:从第一个 token 开始对齐

作者:

Julian Minder

日期:

八月 13, 2026

引用次数:

常见问题

什么是 MATS 项目?
项目持续多久?