Deep Learning

Jailbreaking LLMs Without Gradients or Priors: Effective Transferable Attacks via Random Local Search
Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard. Preprint 2025
Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard
Cite
Jailbreaking LLMs Without Gradients or Priors: Effective Transferable Attacks via Random Local Search
Adaptive Certified Training: Towards Better Accuracy-Robustness Tradeoffs
Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard. In ECML PKDD 2024
Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard
PDF Cite Code DOI
Adaptive Certified Training: Towards Better Accuracy-Robustness Tradeoffs
Universe Points Representation Learning for Partial Multi-Graph Matching
Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard. In AAAI 2023 (Oral Presentation)
Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard
PDF Cite DOI
Universe Points Representation Learning for Partial Multi-Graph Matching