{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/archilles-heel-in-semi-open-llms-hiding","title":"Position: On-Premises LLM Deployment Demands a Middle Path: Preserving Privacy Without Sacrificing Model Confidentiality","arxiv_id":"2410.11182","date":"2024-10-15","proceeding":null,"authors":["Hanbo Huang","Yihan Li","Bowen Jiang","Lin Liu","Bo Jiang","Ruoyu Sun","Zhuotao Liu","Shiyu Liang"],"abstract":"Current LLM customization typically relies on two deployment strategies: closed-source APIs, which require users to upload private data to external servers, and open-weight models, which allow local fine-tuning but pose misuse risks. In this position paper, we argue that (1) deploying closed-source LLMs within user-controlled infrastructure (\\textit{on-premises deployment}) enhances data privacy and mitigates misuse risks, and (2) a well-designed on-premises deployment must ensure model confidentiality -- by preventing model theft -- and offer privacy-preserving customization. Prior research on small models has explored securing only the output layer within hardware-secured devices to balance confidentiality and customization efficiency. However, we show that this approach is insufficient for defending large-scale LLMs against distillation attacks. We therefore introduce a {semi-open deployment framework} that secures only a few, carefully chosen layers, achieving distillation resistance comparable to fully secured models while preserving fine-tuning flexibility. Through extensive experiments, we show that securing bottom layers significantly reduces functional extraction risks. Our findings demonstrate that privacy and confidentiality can coexist, paving the way for secure on-premises AI deployment that balances usability and protection.","url_abs":"https://arxiv.org/abs/2410.11182v2","url_pdf":"https://arxiv.org/pdf/2410.11182v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"archilles-heel-in-semi-open-llms-hiding","repo_url":"https://github.com/OTTO-OTO/SCARA-Semi-Open","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Position"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.11182","atlas_url":"https://app.syntology.ai/?focus=2410.11182","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2410.11182"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2410.11182\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2410.11182"},"call":"get_concepts_for_paper(arxiv_id=\"2410.11182\")"}],"by_repo":[{"repo":"OTTO-OTO/SCARA-Semi-Open","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c80a0d12d4bf3f676d8ca79d401b1b7cae312faa7984f8079c437a9f962663c1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}