5 papers
How does the optimizer implicitly bias the model merging loss landscape?
Chenxiang Zhang, Alexander Theus, Damien Teney +3
Model merging combines independent solutions with different capabilities into a single one while maintaining the same inference cost. Two popular approaches are linear interpolatio…
Unlinkability and History Preserving Bisimilarity
Clément Aubert, Ross Horne, Christian Johansen +1
An ever-increasing number of critical infrastructures rely heavily on the assumption that security protocols satisfy a wealth of requirements. Hence, the importance of certifying e…
Bits for Privacy: Evaluating Post-Training Quantization via Membership Inference
Chenxiang Zhang, Tongxi Qu, Zhong Li +3
Deep neural networks are widely deployed with quantization techniques to reduce memory and computational costs by lowering the numerical precision of their parameters. While quanti…
Spurious Privacy Leakage in Neural Networks
Chenxiang Zhang, Jun Pang, Sjouke Mauw
Neural networks trained on real-world data often exhibit biases while simultaneously being vulnerable to privacy attacks aimed at extracting sensitive information. Despite extensiv…
Empirical Evaluation of Memory-Erasure Protocols
Reynaldo Gil-Pons, Sjouke Mauw, Rolando Trujillo-Rasua
Software-based memory-erasure protocols are two-party communication protocols where a verifier instructs a computational device to erase its memory and send a proof of erasure. The…