Conflict-Free Policy Languages for Probabilistic ML Predicates: A Framework and Case Study with the Semantic Router DSL
Xunzhuo Liu, Hao Wu, Huamin Chen, Bowei He, Xue Liu

TL;DR
This paper introduces a framework for conflict detection in probabilistic ML-based policy languages, proposing a softmax-based partitioning method to prevent silent conflicts without retraining, demonstrated in the Semantic Router DSL.
Contribution
It characterizes conflict detection as a hierarchy and offers a practical softmax-based solution for embedding conflicts in policy languages, implemented in a production routing language.
Findings
Embedding conflicts can be prevented with softmax partitioning.
The hierarchy clarifies decidability levels for different conflict types.
Implementation in Semantic Router DSL shows practical effectiveness.
Abstract
Conflict detection in policy languages is a solved problem -- as long as every rule condition is a crisp Boolean predicate. BDDs, SMT solvers, and NetKAT all exploit that assumption. But a growing class of routing and access-control systems base their decisions on probabilistic ML signals: embedding similarities, domain classifiers, complexity estimators. Two such signals, declared over categories the author intended to be disjoint, can both clear their thresholds on the same query and silently route it to the wrong model. Nothing in the compiler warns about this. We characterize the problem as a three-level decidability hierarchy -- crisp conflicts are decidable via SAT, embedding conflicts reduce to spherical cap intersection, and classifier conflicts are undecidable without distributional knowledge -- and show that for the embedding case, which dominates in practice, replacing…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsFormal Methods in Verification · Network Packet Processing and Optimization · Access Control and Trust
