The Limits of Query Monitoring against Distributed Model Extraction
cs.CR, cs.LG
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/nssprogrammer/query-monitoring
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Localized phase for the Erd\H{o}s-R'enyi graph
- SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
- Training Verifiers to Solve Math Word Problems
- Let Them Steal: Trapping Large Language Model Extraction Attacks with Knowledge Honeypot
- Lossless Anti-Distillation Sampling
- The Spectral Edge of Constant Degree Erd\H{o}s-R'{e}nyi Graphs
- Distilling the Knowledge in a Neural Network
- An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic
- Qwen2.5 Technical Report
- HODA: Hardness-Oriented Detection of Model Extraction Attacks
- FDINet: Protecting against DNN Model Extraction via Feature Distortion Index
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs