5 citations · 12 across the 4 of their papers we have counts for
4 papers
Do Transformers know symbolic rules, and would we know if they did?
Tommi Gröndahl, Yujia Guo, N. Asokan
To improve the explainability of leading Transformer networks used in NLP, it is important to tease apart genuine symbolic rules from merely associative input-output patterns. Howe…
Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Models
Sebastian Szyller, Vasisht Duddu, Tommi Gröndahl +1
Machine learning models are typically made available to potential client users via inference APIs. Model extraction attacks occur when a malicious client uses information gleaned f…
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 -…
OmniShare: Securely Accessing Encrypted Cloud Storage from Multiple Authorized Devices
Andrew Paverd, Sandeep Tamrakar, Hoang Long Nguyen +6
Cloud storage services like Dropbox and Google Drive are widely used by individuals and businesses. Two attractive features of these services are 1) the automatic synchronization o…