Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Nikhil Kapoor

Nikhil Kapoor

Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety

Apr 29, 2021
Sebastian Houben, Stephanie Abrecht, Maram Akila, Andreas Bär, Felix Brockherde, Patrick Feifel, Tim Fingscheidt, Sujan Sai Gannamaneni, Seyed Eghbal Ghobadi, Ahmed Hammam, Anselm Haselhoff, Felix Hauser, Christian Heinzemann, Marco Hoffmann, Nikhil Kapoor, Falk Kappel, Marvin Klingner, Jan Kronenberger, Fabian Küppers, Jonas Löhdefink, Michael Mlynarski, Michael Mock, Firas Mualla, Svetlana Pavlitskaya, Maximilian Poretschkin, Alexander Pohl, Varun Ravi-Kumar, Julia Rosenzweig, Matthias Rottmann, Stefan Rüping, Timo Sämann, Jan David Schneider, Elena Schulz, Gesina Schwalbe, Joachim Sicking, Toshika Srivastava, Serin Varghese, Michael Weber, Sebastian Wirkert, Tim Wirtz, Matthias Woehrle

* 94 pages

Access Paper or Ask Questions

The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing

Jan 13, 2021
Andreas Bär, Jonas Löhdefink, Nikhil Kapoor, Serin J. Varghese, Fabian Hüger, Peter Schlicht, Tim Fingscheidt

Figure 1 for The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing

Figure 2 for The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing

Figure 3 for The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing

Figure 4 for The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing

* IEEE Signal Processing Magazine (Volume: 38, Issue: 1, Jan. 2021), pp. 42 - 52

Access Paper or Ask Questions

A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs

Dec 02, 2020
Nikhil Kapoor, Chun Yuan, Jonas Löhdefink, Roland Zimmermann, Serin Varghese, Fabian Hüger, Nico Schmidt, Peter Schlicht, Tim Fingscheidt

Figure 1 for A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs

Figure 2 for A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs

Figure 3 for A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs

Figure 4 for A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs

* Accepted at ACM CSCS 2020 (8 pages, 4 figures)

Access Paper or Ask Questions

Risk Assessment for Machine Learning Models

Nov 09, 2020
Paul Schwerdtner, Florens Greßner, Nikhil Kapoor, Felix Assion, René Sass, Wiebke Günther, Fabian Hüger, Peter Schlicht

Figure 1 for Risk Assessment for Machine Learning Models

Figure 2 for Risk Assessment for Machine Learning Models

Figure 3 for Risk Assessment for Machine Learning Models

Figure 4 for Risk Assessment for Machine Learning Models

* 8 pages, 5 figures, conference workshop

Access Paper or Ask Questions