activity
20182020
collaborators

6 papers

cs.CL2020

A little goes a long way: Improving toxic language classification despite data scarcity

Mika Juuti, Tommi Gröndahl, Adrian Flanagan +1

Detection of some types of toxic language is hampered by extreme scarcity of labeled training data. Data augmentation - generating new synthetic data from a labeled seed dataset -…

cs.LG2019

Extraction of Complex DNN Models: Real Threat or Boogeyman?

Buse Gul Atli, Sebastian Szyller, Mika Juuti +2

Recently, machine learning (ML) has introduced advanced solutions to many domains. Since ML models provide business advantage to model owners, protecting intellectual property of M…

cs.LG2019

Making targeted black-box evasion attacks effective and efficient

Mika Juuti, Buse Gul Atli, N. Asokan

We investigate how an adversary can optimally use its query budget for targeted evasion attacks against deep neural networks in a black-box setting. We formalize the problem settin…

cs.CL2018

All You Need is "Love": Evading Hate-speech Detection

Tommi Gröndahl, Luca Pajola, Mika Juuti +2

With the spread of social networks and their unfortunate use for hate speech, automatic detection of the latter has become a pressing problem. In this paper, we reproduce seven sta…

cs.CR2018

Stay On-Topic: Generating Context-specific Fake Restaurant Reviews

Mika Juuti, Bo Sun, Tatsuya Mori +1

Automatically generated fake restaurant reviews are a threat to online review systems. Recent research has shown that users have difficulties in detecting machine-generated fake re…

cs.CR2018

PRADA: Protecting against DNN Model Stealing Attacks

Mika Juuti, Sebastian Szyller, Samuel Marchal +1

Machine learning (ML) applications are increasingly prevalent. Protecting the confidentiality of ML models becomes paramount for two reasons: (a) a model can be a business advantag…