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

Add to Chrome

Add to Firefox

Picture for Svetlana Pavlitskaya

Svetlana Pavlitskaya

Measuring Overfitting in Convolutional Neural Networks using Adversarial Perturbations and Label Noise

Sep 27, 2022
Svetlana Pavlitskaya, Joël Oswald, J. Marius Zöllner

Figure 1 for Measuring Overfitting in Convolutional Neural Networks using Adversarial Perturbations and Label Noise

Figure 2 for Measuring Overfitting in Convolutional Neural Networks using Adversarial Perturbations and Label Noise

Figure 3 for Measuring Overfitting in Convolutional Neural Networks using Adversarial Perturbations and Label Noise

Figure 4 for Measuring Overfitting in Convolutional Neural Networks using Adversarial Perturbations and Label Noise

* Accepted for publication at IEEE Symposium on Deep Learning at IEEE SSCI 2022

Access Paper or Ask Questions

Suppress with a Patch: Revisiting Universal Adversarial Patch Attacks against Object Detection

Sep 27, 2022
Svetlana Pavlitskaya, Jonas Hendl, Sebastian Kleim, Leopold Müller, Fabian Wylczoch, J. Marius Zöllner

Figure 1 for Suppress with a Patch: Revisiting Universal Adversarial Patch Attacks against Object Detection

Figure 2 for Suppress with a Patch: Revisiting Universal Adversarial Patch Attacks against Object Detection

Figure 3 for Suppress with a Patch: Revisiting Universal Adversarial Patch Attacks against Object Detection

Figure 4 for Suppress with a Patch: Revisiting Universal Adversarial Patch Attacks against Object Detection

* Accepted for publication at ICECCME 2022

Access Paper or Ask Questions

Adversarial Vulnerability of Temporal Feature Networks for Object Detection

Aug 23, 2022
Svetlana Pavlitskaya, Nikolai Polley, Michael Weber, J. Marius Zöllner

Figure 1 for Adversarial Vulnerability of Temporal Feature Networks for Object Detection

Figure 2 for Adversarial Vulnerability of Temporal Feature Networks for Object Detection

Figure 3 for Adversarial Vulnerability of Temporal Feature Networks for Object Detection

Figure 4 for Adversarial Vulnerability of Temporal Feature Networks for Object Detection

* Accepted for publication at ECCV 2022 SAIAD workshop

Access Paper or Ask Questions

Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection

Jul 15, 2022
Svetlana Pavlitskaya, Bianca-Marina Codău, J. Marius Zöllner

Figure 1 for Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection

Figure 2 for Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection

Figure 3 for Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection

Figure 4 for Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection

* Accepted for publication at the IJCAI 2022 AISafety workshop

Access Paper or Ask Questions

Is Neuron Coverage Needed to Make Person Detection More Robust?

Apr 21, 2022
Svetlana Pavlitskaya, Şiyar Yıkmış, J. Marius Zöllner

Figure 1 for Is Neuron Coverage Needed to Make Person Detection More Robust?

Figure 2 for Is Neuron Coverage Needed to Make Person Detection More Robust?

Figure 3 for Is Neuron Coverage Needed to Make Person Detection More Robust?

Figure 4 for Is Neuron Coverage Needed to Make Person Detection More Robust?

* Accepted for publication at CVPR 2022 TCV workshop

Access Paper or Ask Questions

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