Adam N. Elmachtoub, Tianyi Lin, Wenxuan Liu · 2026 · arXiv
DOI: 10.48550/arXiv.2610.29918 · open-access PDF
考虑一个背景线性优化问题,其中一个预测然后优化(PTO)系统返回最佳决策,而不揭示其下游线性程序中使用的成本向量。我们的重点是如何防止可以提交背景查询的攻击者提取潜在的预测模型。尽管成本对决策的地图是多对一的,但跨背景的观察可以揭示潜在的预测模型。对于线性模型,我们提供足够的条件,让攻击者只能通过观察决定来学习模型,以达到积极的规模。
Machine translation (Meta M2M100); the English original follows.
Consider a contextual linear optimization problem, where a predict-then-optimize (PTO) system returns optimal decisions without revealing the cost vectors used in its downstream linear program. Our focus is on how to prevent attackers, who can submit context queries, from extracting the underlying prediction model. Although the cost-to-decision map is many-to-one, observations across contexts can reveal the underlying prediction model. For linear models, we provide sufficient conditions where the attacker can learn the model up to positive scaling by only observing the decision. These conditio
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29918, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange