Recently, in IEEE Transactions on Dependable and Secure Computing (TDSC), the VERSA scheme proposed by Hahnet al. uses a double aggregation method for verifying the correctness of results returned from the server. The authors proposed that the correctness of the model aggregation can be verified with lower verification overhead by utilizing only a lightweight pseudorandom generator. To support verifiability of results returned from the server, a method of sharing a pair of vectors$(a,b)$by all clients is proposed, which is one of the most important work in VERSA. Unfortunately, in this paper, we show that the method is incorrect, which leads clients to consistently conclude that the aggregated results are incorrect. Furthermore, the model training process in federated learning is forced to abort. Finally, we demonstrate our view through theory analysis and instantiation verification.

Recent works have demonstrated that text classifiers are vulnerable to universal adversarial triggers (UATs), which are concatenated to any original text from the dataset to mislead text classifiers. Existing methods for generating UATs are limited to a white-box setting, where the adversary needs access to the gradient information about the target model. In the more practical black-box setting, the adversary can only access the logit output of the target model, which increases the difficulty of crafting UATs. In this paper, we propose a framework for generating natural UATs using generative adversarial networks (NUAT-GAN) in the black-box setting. To update parameters of the generator in the black-box setting, we design a training generator algorithm with policy gradient (TGPG), in which the gradient of the target model is replaced with the policy gradient of reinforcement learning. On three text classification datasets, we evaluate the attack and the natural performance of UATs generated on LSTM, CNN and BERT models. Results show that UATs generated by NUAT-GAN can mislead the above models. The average values of the Attack Success Rate (ASR) and GPT-2 Loss of UATs are 0.81 and 9.10, respectively. The UATs can effectively attack online models, such as AllenNLP and ChatGPT. Moreover, we replace the reward given by the discriminator with GPT-2 Loss, the attack and the natural performance of UATs are close to those of NUAT-GAN. This shows that NUAT-GAN is extensible and can combined with the language model.

With the rapid development of the Internet of Things (IoT), more IoT devices are connected in the same network and communicate frequently for sharing data and switching instructions. So that the traditional centralized security architecture of IoT will be limited in terms of data storage space, data reliability, scalability, and operating costs. In this article, we propose a novel communication data management model based on blockchain technology. Specifically, all encrypted IoT communication data files are uploaded to the public cloud server for obtaining enough storage space, but the key information extracted from these data files (called “communication logs”) will be recorded in an “IoT ledger” maintained by all IoT devices. In fact, the IoT ledger is a kind of blockchain structured distributed database, which can solve the problem of data reliability, scalability and would not involve high operating costs. Besides, in order to efficiently search communication logs and not reveal any sensitive information of communication data, we design a secure search scheme over such blockchain database, the asymmetric scalar-product-preserving encryption (ASPE) approach is exploited to guarantee the data security, and the two layers index improves the search efficiency. Security analysis and experiments on synthetic data set show that our scheme is secure and efficient.

Dynamic searchable encryption (SE) aims at achieving varied search function over encrypted database in dynamic setting, which is a trade-off in efficiency, security, and functionality. Recent work proposes a file-injection attack which can successfully attack by utilizing some information leaked in the update process. To mitigate this attack, some SE schemes with forward privacy are proposed. However, these schemes are designed to achieve single keyword or conjunctive keyword search, which cannot support multikeyword search. Moreover, these schemes do not consider the function of results ranking. In this paper, we propose a forward privacy multikeyword ranked search scheme over encrypted database. We design a forward privacy multikeyword search scheme based on the classic MRSE scheme. Our scheme makes the cloud cannot obtain the actual match results of the past query with the newly updated files by adding the well-chosen dummy elements to the original index and query vectors. We rank the search results based on the matched keyword number and the T F × I D F $TF\times IDF$ rule in the dynamic setting. Our scheme uses only the symmetric encryption primitive. We implement our scheme for COVID-19 data set and the experimental evaluation results show that the proposed scheme is secure and efficient.