M
Mika Juuti
Researcher at Aalto University
Publications - 24
Citations - 1406
Mika Juuti is an academic researcher from Aalto University. The author has contributed to research in topics: Authentication & Divergence (statistics). The author has an hindex of 10, co-authored 24 publications receiving 865 citations. Previous affiliations of Mika Juuti include University of Waterloo & Helsinki University of Technology.
Papers
More filters
Proceedings ArticleDOI
Oblivious Neural Network Predictions via MiniONN Transformations
TL;DR: MiniONN is presented, the first approach for transforming an existing neural network to an oblivious neural network supporting privacy-preserving predictions with reasonable efficiency and it is shown that MiniONN outperforms existing work in terms of response latency and message sizes.
Proceedings ArticleDOI
PRADA: Protecting Against DNN Model Stealing Attacks
TL;DR: In this article, the authors proposed a generic and effective detection of DNN model extraction attacks by generating synthetic queries and optimizing training hyperparameters, which outperformed state-of-the-art model extraction in terms of transferability of both targeted and non-targeted adversarial examples.
Posted Content
PRADA: Protecting against DNN Model Stealing Attacks
TL;DR: The first step towards generic and effective detection of DNN model extraction attacks is proposed, PRADA, which analyzes the distribution of consecutive API queries and raises an alarm when this distribution deviates from benign behavior, and it is shown that PRADA can detect all priormodel extraction attacks with no false positives.
Posted Content
All You Need is "Love": Evading Hate-speech Detection
TL;DR: It is argued that for successful hate speech detection, model architecture is less important than the type of data and labeling criteria, and all proposed detection techniques are brittle against adversaries who can (automatically) insert typos, change word boundaries or add innocuous words to the original hate speech.
Proceedings ArticleDOI
All You Need is "Love": Evading Hate Speech Detection
TL;DR: In this paper, the authors reproduce seven state-of-the-art hate speech detection models from prior work, and show that they perform well only when tested on the same type of data they were trained on.