Search Results for author:
Found 3 papers, 0 papers with code
Closing the Gap: Achieving Better Accuracy-Robustness Tradeoffs against Query-Based Attacks
Although promising, existing defenses against query-based attacks share a common limitation: they offer increased robustness against attacks at the price of a considerable accuracy drop on clean samples.
On the Synchronization Power of Token Smart Contracts
More surprisingly, the synchronization power of ERC20 tokens depends on the object's state and can thus be modified by method invocations.
Distributed, Parallel, and Cluster Computing Cryptography and Security
BaFFLe: Backdoor detection via Feedback-based Federated Learning
In this paper, we propose Backdoor detection via Feedback-based Federated Learning (BAFFLE), a novel defense to secure FL against backdoor attacks.
