Klas Leino

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 29

Top Topics

Coordinate Ascent

Top Venues

USENIX Security Symposium

Publications

Kai Hu, Klas Leino, Zifan Wang, Matt Fredrikson
A Recipe for Improved Certifiable Robustness. ICLR (2024)
Kai Hu, Andy Zou, Zifan Wang, Klas Leino, Matt Fredrikson
Unlocking Deterministic Robustness Certification on ImageNet. NeurIPS (2023)
Kai Hu, Klas Leino, Zifan Wang, Matt Fredrikson
A Recipe for Improved Certifiable Robustness: Capacity and Data. CoRR (2023)
Klas Leino
Limitations of Piecewise Linearity for Efficient Robustness Certification. CoRR (2023)
Ravi Mangal, Klas Leino, Zifan Wang, Kai Hu, Weicheng Yu, Corina S. Pasareanu, Anupam Datta, Matt Fredrikson
Robustness Still Worthwhile? CoRR (2023)
Kai Hu, Andy Zou, Zifan Wang, Klas Leino, Matt Fredrikson
Scaling in Depth: Unlocking Robustness Certification on ImageNet. CoRR (2023)
Ravi Mangal, Zifan Wang, Chi Zhang, Klas Leino, Corina S. Pasareanu, Matt Fredrikson
On the Perils of Cascading Robust Classifiers. ICLR (2023)
Klas Leino, Aymeric Fromherz, Ravi Mangal, Matt Fredrikson, Bryan Parno, Corina S. Pasareanu
Self-correcting Neural Networks for Safe Classification. NSV/FoMLAS@CAV (2022)
Klas Leino, Chi Zhang, Ravi Mangal, Matt Fredrikson, Bryan Parno, Corina S. Pasareanu
Degradation Attacks on Certifiably Robust Neural Networks. Trans. Mach. Learn. Res. 2022 (2022)
Ravi Mangal, Zifan Wang, Chi Zhang, Klas Leino, Corina S. Pasareanu, Matt Fredrikson
On the Perils of Cascading Robust Classifiers. CoRR (2022)
Emily Black, Klas Leino, Matt Fredrikson
Selective Ensembles for Consistent Predictions. ICLR (2022)
Emily Black, Klas Leino, Matt Fredrikson
Selective Ensembles for Consistent Predictions. CoRR (2021)
Klas Leino, Aymeric Fromherz, Ravi Mangal, Matt Fredrikson, Bryan Parno, Corina S. Pasareanu
Self-Repairing Neural Networks: Provable Safety for Deep Networks via Dynamic Repair. CoRR (2021)
Anupam Datta, Matt Fredrikson, Klas Leino, Kaiji Lu, Shayak Sen, Ricardo Shih, Zifan Wang
Exploring Conceptual Soundness with TruLens. NeurIPS (Competition and Demos) (2021)
Klas Leino, Zifan Wang, Matt Fredrikson
Globally-Robust Neural Networks. ICML (2021)
Aymeric Fromherz, Klas Leino, Matt Fredrikson, Bryan Parno, Corina S. Pasareanu
Fast Geometric Projections for Local Robustness Certification. ICLR (2021)
Klas Leino, Matt Fredrikson
Relaxing Local Robustness. CoRR (2021)
Anupam Datta, Matt Fredrikson, Klas Leino, Kaiji Lu, Shayak Sen, Zifan Wang
Machine Learning Explainability and Robustness: Connected at the Hip. KDD (2021)
Klas Leino, Zifan Wang, Matt Fredrikson
Globally-Robust Neural Networks. CoRR (2021)
Klas Leino, Matt Fredrikson
Relaxing Local Robustness. NeurIPS (2021)
Klas Leino, Matt Fredrikson
Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference. USENIX Security Symposium (2020)
Kaiji Lu, Piotr Mardziel, Klas Leino, Matt Fredrikson, Anupam Datta
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models. ACL (2020)
Kaiji Lu, Piotr Mardziel, Klas Leino, Matt Fredrikson, Anupam Datta
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models. CoRR (2020)
Aymeric Fromherz, Klas Leino, Matt Fredrikson, Bryan Parno, Corina S. Pasareanu
Fast Geometric Projections for Local Robustness Certification. CoRR (2020)
Klas Leino, Emily Black, Matt Fredrikson, Shayak Sen, Anupam Datta
Feature-Wise Bias Amplification. ICLR (Poster) (2019)
Klas Leino, Matt Fredrikson
Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference. CoRR (2019)
Klas Leino, Shayak Sen, Anupam Datta, Matt Fredrikson, Linyi Li
Influence-Directed Explanations for Deep Convolutional Networks. ITC (2018)
Klas Leino, Matt Fredrikson, Emily Black, Shayak Sen, Anupam Datta
Feature-Wise Bias Amplification. CoRR (2018)
Klas Leino, Linyi Li, Shayak Sen, Anupam Datta, Matt Fredrikson
Influence-Directed Explanations for Deep Convolutional Networks. CoRR (2018)