Month: March 2023

To obtain, deterministic guarantees of adversarial robustness, specialized training methods are used. We propose, SABR, a novel such certified training method, based on the key insight that propagating interval bounds…

Machine learning (ML) models are costly to train as they can require a significant amount of data, computational resources and technical expertise. Thus, they constitute valuable intellectual property that needs…

Relativity Space’s attempt to reach orbit heralds the increasing use of 3D printing in the space sector.

Contrastive learning (CL) pre-trains general-purpose encoders using an unlabeled pre-training dataset, which consists of images or image-text pairs. CL is vulnerable to data poisoning based backdoor attacks (DPBAs), in which…

Federated learning has recently been applied to recommendation systems to protect user privacy. In federated learning settings, recommendation systems can train recommendation models only collecting the intermediate parameters instead of…

Contrastive learning (CL) pre-trains general-purpose encoders using an unlabeled pre-training dataset, which consists of images or image-text pairs. CL is vulnerable to data poisoning based backdoor attacks (DPBAs), in which…

Celebrate everyone’s favorite red-capped plumber with a discount on a special Nintendo Switch and classic games.

Transfer adversarial attacks raise critical security concerns in real-world, black-box scenarios. However, the actual progress of this field is difficult to assess due to two common limitations in existing evaluations.…

While anonymity networks like Tor aim to protect the privacy of their users, they are vulnerable to traffic analysis attacks such as Website Fingerprinting (WF) and Flow Correlation (FC). Recent…

Federated learning has recently been applied to recommendation systems to protect user privacy. In federated learning settings, recommendation systems can train recommendation models only collecting the intermediate parameters instead of…