Asja Fischer
Institution: Ruhr-Universität Bochum / CASA
Research Hub(s):
Hub C: Sichere Systeme
E-Mail: Asja.Fischer@rub.de
Adresse: IB 3/153
Website: https://informatik.rub.de/ml/
Publikationen:
Are Semantic Watermarks for Diffusion Models Resilient to Layout Control? Copula-Based Normalizing Flows Thresholded Adaptive Validation: Tuning the Graphical Lasso for Graph Recovery Learning Sparse Codes with Entropy-Based ELBOs Benchmarking the Fairness of Image Upsampling Methods DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distribution Layer-wise linear mode connectivity Information Plane Analysis for Dropout Neural Networks Robustifying automatic speech recognition by extracting slowly varying features Towards a Correct Usage of Cryptography in Semantic Watermarks for Diffusion Models Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models AI-Generated Faces in the Real World: A Large-Scale Case Study of Twitter Profile Images Reassessing Noise Augmentation Methods in the Context of Adversarial Speech Characteristics of Monte Carlo Dropout in Wide Neural Networks Wasserstein dropout SmoothLRP: Smoothing LRP by Averaging over Stochastic Input Variations Approaches to Uncertainty Quantification in Federated Deep Learning Efficient Calculation of Adversarial Examples for Bayesian Neural Networks Detecting Compositionally Out-of-Distribution Examples in Semantic Parsing Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification Leveraging Frequency Analysis for Deep Fake Image Recognition Uncertainty quantification with compound density network How Sampling Impacts the Robustness of Stochastic Neural Networks Marginal Tail-Adaptive Normalizing Flows Uncertainty-Based Detection of Adversarial Attacks in Semantic Segmentation Uncertainty-Weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation A Representative Study on Human Detection of Artificially Generated Media Across Countries AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error Towards the Detection of Diffusion Model Deepfakes
