Adaptive and robust watermark against model extraction attack

arXiv:2405.02365v1 Announce Type: new
Abstract: Large language models have boosted Large Models as a Service (LMaaS) into a thriving business sector. But even model owners offering only API access while keeping model parameters and internal workings private, their Intellectual Property (IP) are still at risk of theft through model extraction attacks. To safeguard the IP of these models and mitigate unfair competition in the language model market, watermarking technology serves as an efficient post-hoc solution for identifying IP infringements. However, …

access api arxiv attack attacks business cs.cr extraction intellectual property internal language language models large model extraction private property risk sector service theft