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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
This paper proposes GuardNN, a secure DNN accelerator that provides hardware-based protection for user data and model parameters even in an untrusted environment. GuardNN shows...