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.

Graph neural networks (GNN) have been widely used in many machine learning tasks, such as text classification, sequence labeling, protein interface prediction, and knowledge graph. With increasing security concerns, GNN have been proved to be vulnerable and unreliable. Recent years, inspired by adversarial model in computer vision, various attacks on graph data begin to emerge. However, the exist attacks mostly focus on security violation and attack specificity, and very few attacks concern error specificity. In this paper, we focus on dealing with this kind of attack on one node of the graph by slightly manipulating the graph structure. Our goal is to change the label of the node to what we want after attack. We formulate this case as label specificity attack problem. The biggest challenge in solving this problem is the lack of theoretical guidance to perform this attack. For this, we reinterpret structural entropy and define differential structural entropy (DS-entropy) to guide the manipulation. Based on DS-entropy, we propose the target-label principle and max-degree principle to execute our attack, and then design the corresponding algorithm DSEM. We compare our algorithm DSEM with two benchmarks on three classical graph data sets. Results show that our algorithm is effective in performing label specificity attacks.

Attribute-based keyword search (ABKS) has a broad developing prospect in providing search service for users and realizing fine-grained access control over ciphertext in the background of cloud computing. However, two open problems prevent further development and application of ABKS. First, most of ABKS schemes suffer from inside keyword guessing attack (KGA) inherently, which is a great threat to the security of the scheme. Second, the existing ABKS schemes focus on single or conjunctive keyword search, these inflexible retrieval modes may lead to efficiency loss caused by inaccurate positioning of user’s interest and greatly reduce user search experience. In this article, we introduce a semi-trusted server and build a dual server model. Based on the dual server model and our proposed techniques, we are the first to put forward an attribute-based multi-keyword ranked search scheme against inside keyword guessing attack (ABKRS-KGA) to solve the mentioned two problems simultaneously. In our scheme, the queries of users contain weighted keywords and the returned files can be ranked according to user’s query interest. We provide strict security definitions for two types of adversaries and we are the first to prove that the construction is adaptively secure against both chosen-keyword attack (CKA) and KGA. Finally, all-side simulation with real-world data set is implemented for the proposed scheme, and the simulation results show that the efficiency of the proposed scheme is acceptable.