Despite the considerable advantages of open-source large language models (LLMs) in terms of interpretability and customizability, the full-access sharing paradigm inevitably exposes them to a severe security threat, i.e., malware embedding attacks (MEAs), where adversaries embed malware binaries (i.e., payloads) into m...
Ming Tan, Wei Li, Tao Hu et al.· Proceedings of the 2026 ACM...· 0 citations
Fine-tuning public pretrained language models with lightweight adapters such as LoRA has become the mainstream way to adapt them to downstream tasks. A service provider often trains its adapter on a data owner's samples, so two assets need protection: the data owner's samples and the provider's adapter. Existing secure...
Hui-Yu Xie, Tan-Ping Zhou, Tao Hu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.