phenomenon · first seen 9 Oct 2026
model extraction attack
Also: model stealing, distillation attack, neural network parameter extraction
Adversarial querying of a deployed model to replicate its capabilities by training a copy on its outputs.
Mentions per week
PapersCodeDiscussion
Earliest sources
- The Limits of Query Monitoring against Distributed Model ExtractionPapers · 9 Oct 2026 · Snigdha Chandan Khilar
- MapSteal: Map-based Autonomous Knowledge Stealing Attack Against Large Language ModelsPapers · 19 Oct 2026 · Zhengao Li, Chuxu Zhang, Yushun Dong
- Preventing Model Extraction in Contextual Linear OptimizationPapers · 21 Oct 2026 · Adam N. Elmachtoub, Tianyi Lin, Wenxuan Liu
- Extraction meets Distillation - cryptanalytic techniques to recover parameters from a Deep Neural NetworkPapers · 24 Oct 2026 · Biprarshi Biswas, Arya Anshuman Ojha, Yubaraj Das, Devansh Khosla, Kamran Rais,…
- Are Spiking Neural Networks Harder to Steal? The Role of Stochastic Encoding in Model ExtractionPapers · 26 Oct 2026 · Ayana Moshruba, Maryam Parsa
- Fingerprinting the Dispatchers behind Distributed Model ExtractionPapers · 4 Nov 2026 · Snigdha Chandan Khilar
Latest sources
- VeilTune: Secure Fine-Tuning of Private LoRA Adapters on Public Pretrained Language ModelsPapers · 9 Nov 2026 · Huiyu Xie, Tanping Zhou, Tao Hu, Xinlei Liu, Hailong Ma
- Cutpurse: Decomposing Explanation-Guided Model Extraction on Tabular DataPapers · 6 Nov 2026 · Seyma Selcan Magara, Hanru Zhang, Fatme El Zahraa Hamad, Nico Pfeifer, Mete Akg…
- Fingerprinting the Dispatchers behind Distributed Model ExtractionPapers · 4 Nov 2026 · Snigdha Chandan Khilar
- Are Spiking Neural Networks Harder to Steal? The Role of Stochastic Encoding in Model ExtractionPapers · 26 Oct 2026 · Ayana Moshruba, Maryam Parsa
- Extraction meets Distillation - cryptanalytic techniques to recover parameters from a Deep Neural NetworkPapers · 24 Oct 2026 · Biprarshi Biswas, Arya Anshuman Ojha, Yubaraj Das, Devansh Khosla, Kamran Rais,…
- Preventing Model Extraction in Contextual Linear OptimizationPapers · 21 Oct 2026 · Adam N. Elmachtoub, Tianyi Lin, Wenxuan Liu
- MapSteal: Map-based Autonomous Knowledge Stealing Attack Against Large Language ModelsPapers · 19 Oct 2026 · Zhengao Li, Chuxu Zhang, Yushun Dong
- The Limits of Query Monitoring against Distributed Model ExtractionPapers · 9 Oct 2026 · Snigdha Chandan Khilar