output
20112026
most citedStealing Machine Learning Models via Prediction APIs

733 citations

Showing 2018 · cs.CRShow all

5 papers · 2 filters

cs.CR2018★ 15 cited

Auditing Data Provenance in Text-Generation Models

Congzheng Song, Vitaly Shmatikov

To help enforce data-protection regulations such as GDPR and detect unauthorized uses of personal data, we develop a new \emph{model auditing} technique that helps users check if t…

cs.CR2018★ 1 cited

More is Less: Perfectly Secure Oblivious Algorithms in the Multi-Server Setting

T-H. Hubert Chan, Jonathan Katz, Kartik Nayak +2

The problem of Oblivious RAM (ORAM) has traditionally been studied in a single-server setting, but more recently the multi-server setting has also been considered. Yet it is still…

cs.CR2018★ 68 cited

Synesthesia: Detecting Screen Content via Remote Acoustic Side Channels

Daniel Genkin, Mihir Pattani, Roei Schuster +1

We show that subtle acoustic noises emanating from within computer screens can be used to detect the content displayed on the screens. This sound can be picked up by ordinary micro…

cs.CR2018★ 428 cited

Ekiden: A Platform for Confidentiality-Preserving, Trustworthy, and Performant Smart Contract Execution

Raymond Cheng, Fan Zhang, Jernej Kos +6

Smart contracts are applications that execute on blockchains. Today they manage billions of dollars in value and motivate visionary plans for pervasive blockchain deployment. While…

cs.CR2018★ 2 cited

When Textbook RSA is Used to Protect the Privacy of Hundreds of Millions of Users

Jeffrey Knockel, Thomas Ristenpart, Jedidiah Crandall

We evaluate Tencent's QQ Browser, a popular mobile browser in China with hundreds of millions of users---including 16 million overseas, with respect to the threat model of a man-in…