Picture for Florian Kerschbaum

Florian Kerschbaum

FastLloyd: Federated, Accurate, Secure, and Tunable $k$-Means Clustering with Differential Privacy

Add code
May 03, 2024
Viaarxiv icon

SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledge

Add code
Feb 22, 2024
Viaarxiv icon

Universal Backdoor Attacks

Add code
Nov 30, 2023
Viaarxiv icon

Leveraging Optimization for Adaptive Attacks on Image Watermarks

Add code
Sep 29, 2023
Viaarxiv icon

Identifying and Mitigating the Security Risks of Generative AI

Add code
Aug 28, 2023
Viaarxiv icon

Backdooring Textual Inversion for Concept Censorship

Add code
Aug 23, 2023
Viaarxiv icon

Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions

Add code
Jun 14, 2023
Viaarxiv icon

Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks against Deep Image Classification

Add code
May 07, 2023
Viaarxiv icon

PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators

Add code
Apr 14, 2023
Viaarxiv icon

Towards Robust Dataset Learning

Add code
Nov 19, 2022
Viaarxiv icon