{"id":"doi:10.1109/tifs.2025.3581103","kind":"article","title":"Hardening LLM Fine-Tuning: From Differentially Private Data Selection to Trustworthy Model Quantization","authors":["Zehang Deng","Ruoxi Sun","Minhui Xue","Wanlun Ma","Sheng Wen","Surya Nepal","Yang Xiang"],"author_count":7,"year":2025,"published":"2025-01-01","venue":"IEEE Transactions on Information Forensics and Security","cited_by":32,"doi":"10.1109/tifs.2025.3581103","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1109/tifs.2025.3581103","archive_url":"https://space-kitty.com/papers/doi:10.1109/tifs.2025.3581103","updated":null,"pmid":null,"pmcid":null,"openalex_id":"W4411408927","pdf_url":null,"abstract":null,"abstract_license":null,"license":null,"is_open_access":false,"retracted":false,"peer_reviewed":null,"categories":["Privacy-Preserving Technologies in Data"],"details":null,"provenance":"openalex","attribution":"Metadata and citation counts: OpenAlex (CC0).","topics":[{"slug":"efficient-ai","name":"Efficient Training & Inference","domain_slug":"ai"}],"cited_in_dossiers":[]}