Authenticated key agreement schemes for multi-server architecture enable a user to register with one registration server and access multiple remote application servers rapidly and conveniently to receive services from them. Several efficient authenticated key agreement schemes have recently been developed for multi-server architecture. However, most of them face many security threats and cannot resist potential attacks. This investigation considers the limitations of previous schemes and proposes a novel efficient and secure multi-server authenticated key agreement scheme that uses Physically Unclonable Functions (PUFs); it is based on a hardware circuit and provides randomness, uniqueness and unclonability to support the lightweight authentication of devices. The proposed scheme protects user privacy and is formally proved to satisfy mutual authentication and session key agreement. This scheme solves problems that were left unsolved in previous works, provides more security, and has a low computational cost.

Adversarial feature alignment is widely used in domain adaptive object detection. Despite the effectiveness on CNN-based detectors, its applicability to transformer-based detectors is less studied. In this paper, we present AQT (adversarial query transformers) to integrate adversarial feature alignment into detection transformers. The generator is a detection transformer which yields a sequence of feature tokens, and the discriminator consists of a novel adversarial token and a stack of cross-attention layers. The cross-attention layers take the adversarial token as the query and the feature tokens from the generator as the key-value pairs. Through adversarial learning, the adversarial token in the discriminator attends to the domain-specific feature tokens, while the generator produces domain-invariant features, especially on the attended tokens, hence realizing adversarial feature alignment on transformers. Thorough experiments over several domain adaptive object detection benchmarks demonstrate that our approach performs favorably against the state-of-the-art methods. Source code is available at https://github.com/weii41392/AQT.