activity
20152019
most citedGuessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attacks

112 citations · 244 across the 7 of their papers we have counts for

collaborators
Showing 2019Show all

5 papers · 1 filter

cs.CV2019★ 1 cited

Copy and Paste: A Simple But Effective Initialization Method for Black-Box Adversarial Attacks

Thomas Brunner, Frederik Diehl, Alois Knoll

Many optimization methods for generating black-box adversarial examples have been proposed, but the aspect of initializing said optimizers has not been considered in much detail. W…

cs.LG2019★ 97 cited

Edge Contraction Pooling for Graph Neural Networks

Frederik Diehl

Graph Neural Network (GNN) research has concentrated on improving convolutional layers, with little attention paid to developing graph pooling layers. Yet pooling layers can enable…

stat.ML2019

Leveraging Semantic Embeddings for Safety-Critical Applications

Thomas Brunner, Frederik Diehl, Michael Truong Le +1

Semantic Embeddings are a popular way to represent knowledge in the field of zero-shot learning. We observe their interpretability and discuss their potential utility in a safety-c…

cs.RO2019★ 26 cited

Bridging the Gap between Open Source Software and Vehicle Hardware for Autonomous Driving

Tobias Kessler, Julian Bernhard, Martin Buechel +7

Although many research vehicle platforms for autonomous driving have been built in the past, hardware design, source code and lessons learned have not been made available for the n…

cs.LG2019

Graph Neural Networks for Modelling Traffic Participant Interaction

Frederik Diehl, Thomas Brunner, Michael Truong Le +1

By interpreting a traffic scene as a graph of interacting vehicles, we gain a flexible abstract representation which allows us to apply Graph Neural Network (GNN) models for traffi…