Collective Robustness Certificates
May 3, 2021
Speakers
Jan Schuchardt
Speaker · 0 followers
Aleksandar Bojchevski
Speaker · 1 follower
Johannes Klicpera
Speaker · 0 followers
Stephan Günnemann
Speaker · 2 followers
About
In tasks like node classification, image segmentation, and named-entity recognition we have a classifier that simultaneously outputs multiple predictions (a vector of labels) based on a single input, i.e. a single graph, image, or document respectively. Existing adversarial robustness certificates consider each prediction independently and are thus overly pessimistic for such tasks. They implicitly assume that an adversary can use different perturbed inputs to attack different predictions, ignoring the fact that we have a single shared input. We propose the first collective robustness certificate which computes the number of predictions which are simultaneously guaranteed to remain stable under perturbation, i.e. cannot be attacked. We focus on Graph Neural Networks and leverage their locality property - perturbations only affect the predictions in a close neighborhood - to fuse multiple single-node certificates into a drastically stronger collective certificate. For example, on the Citeseer dataset our collective certificate for node classification increases the number of average certifiable feature perturbations from $7$ to $351$.In tasks like node classification, image segmentation, and named-entity recognition we have a classifier that simultaneously outputs multiple predictions (a vector of labels) based on a single input, i.e. a single graph, image, or document respectively. Existing adversarial robustness certificates consider each prediction independently and are thus overly pessimistic for such tasks. They implicitly assume that an adversary can use different perturbed inputs to attack different predictions, ignor…
About ICLR 2021
The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Learning and Evaluating Representations for Deep One-Class Classification
Watch later
Kihyuk Sohn, …
Leveraging Public Data in Practical Private Query Release
Watch later
Terrance Liu, …
Self-training Algorithms and Analyses for Unsupervised Domain Adaptation
Watch later
Batch Reinforcement Learning Through Continuation Method
Watch later
Yijie Guo, …
Direct Federated Neural Architecture Search
Watch later
Anubhav Garg, …
