February 27, 2023 Ilkan Esiyok, Pascal Berrang, Katriel Cohn-Gordon, Robert Kunnemann Paper Accountable JavaScript Code Delivery We propose Accountable JS, a browser extension and opt-in protocol for accountable delivery of active content on a web page. We prototype our protocol, formally model its... Areas Networking & Connectivity , Security & Privacy , Paper
February 27, 2023 Harjasleen Malvai, Lefteris Kokoris-Kogias, Alberto Sonnino, Esha Ghosh, Ercan Ozturk, Kevin Lewi, Sean Lawlor Paper Parakeet: Practical Key Transparency for End-to-End Encrypted Messaging We enumerate these challenges and provide solutions to address them. In particular, we design and implement a memory-optimized and privacy-preserving verifiable data structure... Areas Security & Privacy Paper
February 8, 2023 Giovanni Apruzzese, Hyrum S. Anderson, Savino Dambra, David Freeman, Fabio Pierazzi, Kevin Roundy Paper “Real Attackers Don’t Compute Gradients”: Bridging the Gap Between Adversarial ML Research and Practice We first present three real-world case studies from which we can glean practical insights unknown or neglected in research. Next we analyze all adversarial ML papers recently... Areas Machine Learning , Security & Privacy , Paper
December 6, 2022 Julian Mackay, Susan Eisenbach, James Noble, Sophia Drossopoulou Paper Necessity Specifications for Robustness Robust modules guarantee to do only what they are supposed to do ? even in the presence of untrusted, malicious clients, and considering not just the direct behavior of... Areas Security & Privacy Paper
December 3, 2022 Shengyuan Hu, Jack Goetz, Kshitiz Malik, Hongyuan Zhan, Zhe Liu, Yue Liu Paper FedSynth: Gradient Compression via Synthetic Data in Federated Learning In this work, we propose a new scheme for upstream communication where instead of transmitting the model update, each client learns and transmits a light-weight synthetic dataset... Areas Artificial Intelligence , Machine Learning , Security & Privacy , Paper
November 27, 2022 Emily Wenger, Mingjie Chen, Francois Charton, Kristin Lauter Paper SALSA: Attacking Lattice Cryptography with Transformers In this work, we train transformers to perform modular arithmetic and mix half-trained models with statistical cryptanalysis techniques to propose SALSA: a machine learning... Areas Artificial Intelligence , Security & Privacy , Paper
November 9, 2022 Samuel Maddock, Graham Cormode, Tianhao Wang, Carsten Maple, Somesh Jha Paper Federated Boosted Decision Trees with Differential Privacy In this work, we implement the GBDT model under Differential Privacy (DP). We propose a general framework that captures and extends existing approaches for differentially... Areas Security & Privacy Paper
September 28, 2022 Rodrigo Otoni, Matteo Marescotti, Leonardo Alt, Patrick Eugster, Antti E. J. Hyvarinen, Natasha Sharygina Paper A Solicitous Approach to Smart Contract Verification In this paper we describe a carefully crafted approach that directly models the central aspects of smart contracts natively, going from the contract to its logical representation... Areas Artificial Intelligence , Security & Privacy , Paper
August 12, 2022 Andreas Hulsing, Matthias Meijers, Pierre-Yves Strub Paper Formal Verification of Saber’s Public-Key Encryption Scheme in EasyCrypt In this work, we consider the formal verification of the public-key encryption scheme of Saber, one of the selected few post-quantum cipher suites currently considered for potential... Areas Networking & Connectivity , Security & Privacy , Paper
July 17, 2022 Gautam Kamath, Xingtu Liu, Huanyu Zhang Paper Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data We study stochastic convex optimization with heavy-tailed data under the constraint of differential privacy (DP). Most prior work on this problem is restricted to the case where... Areas Artificial Intelligence , Machine Learning , Security & Privacy , Paper