Search Results for author:
Found 5 papers, 2 papers with code
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.
Assessing Robustness via Score-Based Adversarial Image Generation
In this work, we introduce Score-Based Adversarial Generation (ScoreAG), a novel framework that leverages the advancements in score-based generative models to generate adversarial examples beyond $\ell_p$-norm constraints, so-called unrestricted adversarial examples, overcoming their limitations.
Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness
We perform the first adversarial robustness study into Graph Neural Networks (GNNs) that are provably more powerful than traditional Message Passing Neural Networks (MPNNs).
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.
