Keita Kurita, Anna Belova and Antonios Anastasopoulos
Towards Robust Toxic Content Classification
Pratik Vaishnavi, Tianji Cong, Kevin Eykholt, Atul Prakash and Amir Rahmati
Can Attention Masks Improve Adversarial Robustness?
Woojin Lee, Sungyoon Lee, Hoki Kim and Jaewook Lee
Sliced Wasserstein Adversarial Training for Defending Against Adversarial Attacks
Peter Santhanam
Quality Management of Deep Learning Systems
Samuel Ackerman, Orna Raz and Marcel Zalmanovici
FreaAI: Automated extraction of data slices to test machine learning models
Parijat Dube and Eitan Farchi
Automated detection of drift in deep learning based classifiers using network embeddings
Guy Barash, Onn Shehory, Sarit Kraus and Eitan Farchi
Learner-Independent Data Omission Attacks
Buse Atli, Sebastian Szyller, Mika Juuti, Samuel Marchal and N. Asokan
Extraction of Complex DNN Models: Real Threat or Boogeyman? [presentation]
Malhar Jere, Sandro Herbig and Christine Lind
Principal Component Properties of Adversarial Samples
Hoa T. Le, Christophe Cerisara and Claire Gardent
Quality of syntactic implication of RL-based sentence summarization
Molly O'Brien, William Goble, Greg Hager and Julia Bukowski
Dependable Neural Networks for Safety Critical Tasks