Federated Learning (FL) is vulnerable to backdoor attacks by design since it cannot inspect clients’ local data to protect their privacy. This privacy-preserving feature creates an opportunity for malicious clients to introduce backdoors. However, existing backdoor attacks face two main limitations. First, brute amplification (i.e., uniformly scaling up malicious parameters) can be easily detected, hence compromising attack stealthiness. Second, evasion strategies employed to prevent their backdoors from being overwritten by benign updates are frequently ineffective, reducing the overall attack stability upon model deployment. To address these limitations, we propose an adaptive proactive boosting strategy to enhance both the stealthiness and durability of backdoor attacks in FL. As a concrete example,ReBAintroduces a durable importance metric based on stability degrees of parameters as an update mask for malicious attackers, assigning higher weights to backdoor-related parameters during the update process. To ensure stealthiness,ReBAformulates an optimization problem regarding amplification factor by minimizing the distance between malicious and clean updates, thereby correcting malicious updates within a benign distance space. Extensive evaluations on 3 datasets and across 14 defenses demonstrate the efficacy ofReBA, outperforming over 12 baseline backdoor attacks. Our code is available at https://anonymous.4open.science/r/ReBA-D82F.

In smart wireless communication environments, specific emitter identification (SEI) technology has become a crucial means to ensure the security and stability of the wireless communication system. With the rapid increase in the number of Internet of Things (IoT) devices, traditional closed-set identification methods are no longer adequate to handle dynamic and complex wireless environments, particularly for unknown and rogue device intrusions. Consequently, open set SEI (OS-SEI) methods have emerged, which not only identify known devices but also effectively detect previously unseen rogue devices, thereby providing enhanced security and reliability. Therefore, this paper proposes an OS-SEI method based on reciprocal points learning and deep reconstruction learning (RPDRL). Firstly, by introducing an attention-based convolutional autoencoder (ACAE) with skip-layer connections (SC), which is used for deep reconstruction learning, along with reciprocal points learning (RPL), the extracted features become more robust. Furthermore, we design a classification algorithm that combines an appropriate fingerprint metric and extreme value theory (EVT), effectively achieving the detection of rogue devices and the classification of known devices. An open-source automatic dependent surveillance-broadcast (ADS-B) dataset and an intercom dataset are used to evaluate the RPDRL-based OS-SEI method. Experimental results indicate that the proposed method achieves an accuracy of 94.88% on the ADS-B dataset and 96.00% on the intercom dataset. Ablation experiments demonstrate the effectiveness of the efficient channel attention (ECA) modules and SC in the proposed network structure, as well as the efficacy of each loss function.