5 papers
Beyond Bit Matching: Orthogonal Watermarks for Collusion-Resistant Image Fingerprinting
Zhakshylyk Nurlanov, Tobias Weißberg, Florian Bernard
Image fingerprinting assigns each distributed copy a user-specific watermark for source tracing. Averaging collusion is a central threat: several recipients can average their diffe…
Jailbreaking LLMs Without Gradients or Priors: Effective and Transferable Attacks
Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard
As Large Language Models (LLMs) are increasingly deployed in safety-critical domains, rigorously evaluating their robustness against adversarial jailbreaks is essential. However, c…
Adaptive Certified Training: Towards Better Accuracy-Robustness Tradeoffs
Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard
As deep learning models continue to advance and are increasingly utilized in real-world systems, the issue of robustness remains a major challenge. Existing certified training meth…
Universe Points Representation Learning for Partial Multi-Graph Matching
Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard
Many challenges from natural world can be formulated as a graph matching problem. Previous deep learning-based methods mainly consider a full two-graph matching setting. In this wo…
Efficient and Flexible Sublabel-Accurate Energy Minimization
Zhakshylyk Nurlanov, Daniel Cremers, Florian Bernard
We address the problem of minimizing a class of energy functions consisting of data and smoothness terms that commonly occur in machine learning, computer vision, and pattern recog…