activity
20172021
collaborators

9 papers

cs.CR2021

Deep Reinforcement Learning for Backup Strategies against Adversaries

Pascal Debus, Nicolas Müller, Konstantin Böttinger

Many defensive measures in cyber security are still dominated by heuristics, catalogs of standard procedures, and best practices. Considering the case of data backup strategies, we…

cs.SD2020

Towards Resistant Audio Adversarial Examples

Tom Dörr, Karla Markert, Nicolas M. Müller +1

Adversarial examples tremendously threaten the availability and integrity of machine learning-based systems. While the feasibility of such attacks has been observed first in the do…

cs.CR2020

Optimizing Information Loss Towards Robust Neural Networks

Philip Sperl, Konstantin Böttinger

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. Th…

cs.LG2020

Data Poisoning Attacks on Regression Learning and Corresponding Defenses

Nicolas Michael Müller, Daniel Kowatsch, Konstantin Böttinger

Adversarial data poisoning is an effective attack against machine learning and threatens model integrity by introducing poisoned data into the training dataset. So far, it has been…

cs.CR2020

: Activation Anomaly Analysis

Philip Sperl, Jan-Philipp Schulze, Konstantin Böttinger

Inspired by recent advances in coverage-guided analysis of neural networks, we propose a novel anomaly detection method. We show that the hidden activation values contain informati…

cs.CR2019

DLA: Dense-Layer-Analysis for Adversarial Example Detection

Philip Sperl, Ching-Yu Kao, Peng Chen +1

In recent years Deep Neural Networks (DNNs) have achieved remarkable results and even showed super-human capabilities in a broad range of domains. This led people to trust in DNNs'…