Dr. Erwin Quiring
  • Bio
  • Publications
  • Experience
  • Publications
    • Are Semantic Watermarks for Diffusion Models Resilient to Layout Control?
    • Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
    • Towards A Correct Usage of Cryptography in Semantic Watermarks for Diffusion Models
    • AI-Generated Faces in the Real World: A Large-Scale Case Study of Twitter Profile Images
    • I still know it's you! On Challenges in Anonymizing Source Code
    • Pitfalls in Machine Learning for Computer Security
    • The Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision
    • Lessons Learned on Machine Learning for Computer Security
    • No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment using Adversarial Learning
    • On the Detection of Image-Scaling Attacks in Machine Learning
    • Dos and Don'ts of Machine Learning in Computer Security
    • Misleading Deep-Fake Detection with GAN Fingerprints
    • Adversarial Preprocessing: Understanding and Preventing Image-Scaling Attacks in Machine Learning
    • Against All Odds: Winning the Defense Challenge in an Evasion Competition with Diversification
    • Backdooring and Poisoning Neural Networks with Image-Scaling Attacks
    • Misleading Authorship Attribution of Source Code using Adversarial Learning
    • On the Security and Applicability of Fragile Camera Fingerprints
    • Adversarial Machine Learning Against Digital Watermarking
    • Forgotten Siblings: Unifying Attacks on Machine Learning and Digital Watermarking
    • Privacy-Enhanced Fraud Detection with Bloom Filters
    • Privacy Threats through Ultrasonic Side Channels on Mobile Devices
    • Bat in the Mobile: A Study on Ultrasonic Device Tracking
    • Fragile Sensor Fingerprint Camera Identification
    • Laiengerechte Erzeugung von 3D-Animationen am Beispiel von textuellen Unfallbeschreibungen
    • On the Combination of Randomized Thresholds and Non-Parametric Boundaries to Protect Digital Watermarks against Sensitivity Attacks
  • Experience

Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models

Jan 1, 2025·
Andreas Müller
,
Denis Lukovnikov
,
Jonas Thietke
,
Asja Fischer
,
Erwin Quiring
· 1 min read

Selected paper for oral presentation

Last updated on Jan 1, 2025
← Are Semantic Watermarks for Diffusion Models Resilient to Layout Control? Jan 1, 2025
Towards A Correct Usage of Cryptography in Semantic Watermarks for Diffusion Models Jan 1, 2025 →

© 2025 Erwin Quiring. This work is licensed under CC BY NC ND 4.0.

Made with Hugo Blox Builder. Clone this template →