Paper ID: 2410.11182

Archilles' Heel in Semi-open LLMs: Hiding Bottom against Recovery Attacks

Hanbo Huang, Yihan Li, Bowen Jiang, Lin Liu, Ruoyu Sun, Zhuotao Liu, Shiyu Liang

Closed-source large language models deliver strong performance but have limited downstream customizability. Semi-open models, combining both closed-source and public layers, were introduced to improve customizability. However, parameters in the closed-source layers are found vulnerable to recovery attacks. In this paper, we explore the design of semi-open models with fewer closed-source layers, aiming to increase customizability while ensuring resilience to recovery attacks. We analyze the contribution of closed-source layer to the overall resilience and theoretically prove that in a deep transformer-based model, there exists a transition layer such that even small recovery errors in layers before this layer can lead to recovery failure. Building on this, we propose \textbf{SCARA}, a novel approach that keeps only a few bottom layers as closed-source. SCARA employs a fine-tuning-free metric to estimate the maximum number of layers that can be publicly accessible for customization. We apply it to five models (1.3B to 70B parameters) to construct semi-open models, validating their customizability on six downstream tasks and assessing their resilience against various recovery attacks on sixteen benchmarks. We compare SCARA to baselines and observe that it generally improves downstream customization performance and offers similar resilience with over \textbf{10} times fewer closed-source parameters. We empirically investigate the existence of transition layers, analyze the effectiveness of our scheme and finally discuss its limitations.

Submitted: Oct 15, 2024