Stealing Machine Learning Models via Prediction APIs
Assessment outcome
total 4/6 (actionability 0 + authority 2 + currency 2)
Authorship & scope
The paper explicitly lists multiple named authors.
Score 2: Peer-reviewed article appearing in conference proceedings.
Issuers, who it governs, legal force and content are on the full record.
Eligibility gates
HTTP 200, 731 words of full text extracted
The page is explicitly about machine learning models, prediction APIs, and model extraction attacks.
Addresses security risks, model confidentiality, and the need for deployment countermeasures.
The paper explicitly lists multiple named authors.
No notice of retraction, withdrawal, or supersession is present on the page.
Scored criteria
Actionability
0/2Score 0: Description or analysis only, detailing model extraction attacks without binding steps.
Authority
2/2Score 2: Peer-reviewed article appearing in conference proceedings.
Proceedings of USENIX Security 2016
Currency
2/2computed: newest date 2026-08-11 (via http-header), ~0.0y old; within the 60-month academic_research window for perspective 'Academic' → 2