Provable Model Provenance Set for Large Language Models
The growing prevalence of unauthorized model usage and misattribution has increased the need for reliable model provenance analysis. However, existing methods largely rely on heuristic fingerprint-matching rules that lack provable error control and often overlook the existence of multiple sources, leaving the reliability of their provenance claims unverified. In this work, we first formalize the model provenance problem with provable guarantees, requiring rigorous coverage of all true provenances at a prescribed confidence level. Then, we propose the Model Provenance Set (MPS), which employs a sequential test-and-exclusion procedure to adaptively construct a small set satisfying the guarantee. The key idea of MPS is to test the significance of provenance existence within a candidate pool, thereby establishing a provable asymptotic guarantee at a user-specific confidence level. Extensive experiments demonstrate that MPS effectively achieves target provenance coverage while strictly limiting the inclusion of unrelated models, and further reveal its potential for practical provenance analysis in attribution and auditing tasks.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Provable unlearning in topic modeling and downstream tasks
Machine unlearning algorithms are increasingly important as legal concerns arise around the provenance of training data, but verifying the success of unlearning is often difficult. Provable guarantees for unlearning are …
Machine UnlearningTopic ModelsLLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology
Modern scientific discovery increasingly relies on workflows that process data across the Edge, Cloud, and High Performance Computing (HPC) continuum. Comprehensive and in-depth analyses of these data are critical for hy…
Anomaly DetectionAn End-to-End Framework for Functionality-Embedded Provenance Graph Construction and Threat Interpretation
Provenance graphs model causal system-level interactions from logs, enabling anomaly detectors to learn normal behavior and detect deviations as attacks. However, existing approaches rely on brittle, manually engineered …
Protecting Context and Prompts: Deterministic Security for Non-Deterministic AI
Large Language Model (LLM) applications are vulnerable to prompt injection and context manipulation attacks that traditional security models cannot prevent. We introduce two novel primitives--authenticated prompts and au…
Enabling Efficient Attack Investigation via Human-in-the-Loop Security Analysis
System auditing is a vital technique for collecting system call events as system provenance and investigating complex multi-step attacks such as Advanced Persistent Threats. However, existing attack investigation methods…