Search Results for author:
Found 11 papers, 2 papers with code
Group Privacy Amplification and Unified Amplification by Subsampling for Rényi Differential Privacy
Differential privacy (DP) has various desirable properties, such as robustness to post-processing, group privacy, and amplification by subsampling, which can be derived independently of each other.
Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
For the first time, we propose a sound notion of adversarial robustness that accounts for task equivariance.
Hierarchical Randomized Smoothing
Randomized smoothing is a powerful framework for making models provably robust against small changes to their inputs - by guaranteeing robustness of the majority vote when randomly adding noise before classification.
Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks
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.
Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks
To remedy this, we propose novel gray-box certificates that exploit the message-passing principle of GNNs: We randomly intercept messages and carefully analyze the probability that messages from adversarially controlled nodes reach their target nodes.
Training Differentially Private Graph Neural Networks with Random Walk Sampling
We propose to solve this issue by training graph neural networks on disjoint subgraphs of a given training graph.
Invariance-Aware Randomized Smoothing Certificates
Building models that comply with the invariances inherent to different domains, such as invariance under translation or rotation, is a key aspect of applying machine learning to real world problems like molecular property prediction, medical imaging, protein folding or LiDAR classification.
Localized Randomized Smoothing for Collective Robustness Certification
We further show that this approach is beneficial for the larger class of softly local models, where each output is dependent on the entire input but assigns different levels of importance to different input regions (e. g. based on their proximity in the image).
Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness
Specifically, most datasets only capture a simpler subproblem and likely suffer from spurious features.
Collective Robustness Certificates
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.
Learning to Evolve
Here we show that learning to evolve, i. e. learning to mutate and recombine better than at random, improves the result of evolution in terms of fitness increase per generation and even in terms of attainable fitness.
