no code implementations • 19 Feb 2022 • Tommi Gröndahl, Yujia Guo, N. Asokan
To facilitate this, we experiment on four sequence modelling tasks on the T5 Transformer in two experiment settings: zero-shot generalization, and generalization across class-specific vocabularies flipped between the training and test set.
no code implementations • 26 Apr 2021 • Sebastian Szyller, Vasisht Duddu, Tommi Gröndahl, N. Asokan
We present a framework for conducting such attacks, and show that an adversary can successfully extract functional surrogate models by querying $F_V$ using data from the same domain as the training data for $F_V$.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Mika Juuti, Tommi Gröndahl, Adrian Flanagan, N. Asokan
Detection of some types of toxic language is hampered by extreme scarcity of labeled training data.
no code implementations • 31 May 2019 • Tommi Gröndahl, N. Asokan
Finally, we highlight a critical problem that afflicts all current style transfer techniques: the adversary can use the same technique for thwarting style transfer via adversarial training.
no code implementations • 25 Feb 2019 • Tommi Gröndahl
We present the first generic semantic representation format for NLP directly based on these insights.
no code implementations • 24 Feb 2019 • Tommi Gröndahl, N. Asokan
Textual deception constitutes a major problem for online security.
no code implementations • 28 Aug 2018 • Tommi Gröndahl, Luca Pajola, Mika Juuti, Mauro Conti, N. Asokan
With the spread of social networks and their unfortunate use for hate speech, automatic detection of the latter has become a pressing problem.