Website Fingerprinting (WF) attack can be mitigated throughrandom camouflageorpair camouflage.Random camouflageinserts random dummy packets into the traces according to pre-defined rules. It can be compromised easily by machine learning-based WF attacks.Pair camouflageobfuscates the distinguishing features of paired websites by inserting elaborated perturbations into raw traces, thereby misleading the attacker. It is costly in maintaining a perturbation generator for each pair of websites. Based on these insights, we proposeStinger, a novel data poisoning based WF defense, which enables effective defense against WF attacks with low bandwidth overhead and only maintains one generator for all websites.Stingerexploits the idea of poisoning by contaminating the model directly in such a way that the WF attacks only classify based on the inserted poison sequences, thus being low overhead and website independent. We experimentally evaluateStingerusing the DF and AWF datasets. The results show that Stinger improves the successful defending rate by an average of 20.37% and 22.83% while reducing overhead by 85.88% and 81.35%, respectively.

Summary With the development of the Internet of Things (IoT), the number of terminal devices is rapidly growing and at the same time, their security is facing serious challenges. For the industrial control system, there are challenges in detecting and preventing botnet. Traditional detection methods focus on capturing and reverse analyzing the botnet programs first and then parsing the extracted features from the malicious code or attacks. However, their accuracy is very low and their latency is relatively high. Moreover, they sometimes even cannot recognize the unknown botnets. The machine learning based detection methods rely on manual feature engineering and have a weak generalization. The deep learning‐based methods mostly rely on the system log, which does not take into account the multisource information such as traffic. To address the above issues, from the perspective of the botnet features, this paper proposes an intelligent detection method over parallel CNN‐LSTM, integrating the spatial and temporal features to identify botnets. Experimental demonstrate that the accuracy, recall, and F1‐score of our proposed method achieve up to over 98%, and the precision, 97.8%, is not the highest but reasonable. It reveals compared with the existing start‐of‐the‐art methods, our proposed method outperforms in the botnet detection. Our methodology's strength lies in its ability to harness the multifaceted information present in IoT traffic, offering a more nuanced and comprehensive analysis. The parallel CNN‐LSTM architecture ensures that spatial and temporal data are processed concurrently, preserving the integrity of the information and enabling a more robust detection mechanism. The result is a detection system that not only performs exceptionally well in a controlled environment but also holds promise for real‐world application, where the rapid and accurate identification of botnets is paramount.

Model quantization can reduce the memory footprint of the neural network and improve the computing efficiency. However, the sparse attention in Transformer models is difficult to quantize, the main challenge is that changing the order of attention values and shifting attention regions might lead to incorrect prediction results. To address this problem, we propose quantization method, termed TAQ, which uses the proposed TOP-K attention-aware loss to search the quantization parameters. Further, we combine the sequential and parallel quantization methods to optimize the procedure. We evaluate the generalization ability of TAQ on various vision Transformer variants, and its performance on image classification and object detection tasks. TAQ makes the TOP-K attention ranking more consistent before and after quantization, and significantly reduces the attention shifting rate, compared with PTQ4ViT, TAQ improves the performance by 0.66 and 0.45, respectively on ImageNet and COCO, achieves the state-of-the-art performance.

BACKGROUND: A number of predictive models for aquatic toxicity are available, however, the accuracy and extent of easy to use of these in silico tools in risk assessment still need further studied. This study evaluated the performance of seven in silico tools to daphnia and fish: ECOSAR, T.E.S.T., Danish QSAR Database, VEGA, KATE, Read Across and Trent Analysis. 37 Priority Controlled Chemicals in China (PCCs) and 92 New Chemicals (NCs) were used as validation dataset. RESULTS: In the quantitative evaluation to PCCs with the criteria of 10-fold difference between experimental value and estimated value, the accuracies of VEGA is the highest among all of the models, both in prediction of daphnia and fish acute toxicity, with accuracies of 100% and 90% after considering AD, respectively. The performance of KATE, ECOSAR and T.E.S.T. is similar, with accuracies are slightly lower than VEGA. The accuracy of Danish Q.D. is the lowest among the above tools with which QSAR is the main mechanism. The performance of Read Across and Trent Analysis is lowest among all of the tested in silico tools. The predictive ability of models to NCs was lower than that of PCCs possibly because never appeared in training set of the models, and ECOSAR perform best than other in silico tools. CONCLUSION: QSAR based in silico tools had the greater prediction accuracy than category approach (Read Across and Trent Analysis) in predicting the acute toxicity of daphnia and fish. Category approach (Read Across and Trent Analysis) requires expert knowledge to be utilized effectively. ECOSAR performs well in both PCCs and NCs, and the application shoud be promoted in both risk assessment and priority activities. We suggest that distribution of multiple data and water solubility should be considered when developing in silico models. Both more intelligent in silico tools and testing are necessary to identify hazards of Chemicals.

A framework for Identification of Risk Factors in Brownfield Redevelopment is proposed from the perspective of an empirical study. Firstly, the selection of the primary set of risk factors of brownfield redevelopment is put forth by the literature research and group decision methods. Then reliability and validity of the primary set of risk factors of brownfield redevelopment is approved by calculating the value of Cronbach's alpha and conducting the KMO (Kaiser-Meyer-Olkin) and Bartlett ball test. Finally, the main risk factors of brownfield redevelopment are identified by carrying out factor analysis. The identified risk factors facilitate risk assessment and control.