Efficient adversarial attack methods are critical for assessing the robustness of computer vision models.In this paper, we reconstruct the optimization objective for generating adversarial examples as "maximizing the difference between the non-true labels' probability upper bound and the true label's probability," and propose a gradient-based attack method termed Sequential Difference Maximization (SDM).SDM establishes a three-layer optimization framework of "cycle-stage-step." The processes between cycles and between iterative steps are respectively identical, while optimization stages differ in terms of loss functions: in the initial stage, the negative probability of the true label is used as the loss function to compress the solution space; in subsequent stages, we introduce the Directional Probability Difference Ratio (DPDR) loss function to gradually increase the non-true labels' probability upper bound by compressing the irrelevant labels' probabilities.Experiments demonstrate that compared with previous SOTA methods, SDM not only exhibits stronger attack performance but also achieves higher attack cost-effectiveness.Additionally, SDM can be combined with adversarial training methods to enhance their defensive effects.The code is available at https://github.com/X-L-Liu/SDM.

Abstract Nowadays, the malicious MS-Office document has already become one of the most effective attacking vectors in APT attacks. Though many protection mechanisms are provided, they have been proved easy to bypass, and the existed detection methods show poor performance when facing malicious documents with unknown vulnerabilities or with few malicious behaviors. In this paper, we first introduce the definition of im-documents, to describe those vulnerable documents which show implicitly malicious behaviors and escape most of public antivirus engines. Then we present GLDOC—a GCN based framework that is aimed at effectively detecting im-documents with dynamic analysis, and improving the possible blind spots of past detection methods. Besides the system call which is the only focus in most researches, we capture all dynamic behaviors in sandbox, take the process tree into consideration and reconstruct both of them into graphs. Using each line to learn each graph, GLDOC trains a 2-channel network as well as a classifier to formulate the malicious document detection problem into a graph learning and classification problem. Experiments show that GLDOC has a comprehensive balance of accuracy rate and false alarm rate − 95.33% and 4.33% respectively, outperforming other detection methods. When further testing in a simulated 5-day attacking scenario, our proposed framework still maintains a stable and high detection accuracy on the unknown vulnerabilities.

Packet classification is a very basic technique in supporting various advanced network services, for example, network measurement, quality of service, flow routing, and so on. Traditional decision tree-based packet classification algorithms often generate many redundant rules. To solve this issue, we propose GroupCuts, which employs two novel ideas. (1) Space relationship-based rule clustering: according to the analysis of classifiers, GroupCuts clusters the rules of similar size and then partitions the classifiers into subgroups. Building decision trees in these sub-groups achieves fine space performance. (2) Dynamic Point Split: in order to reduce the rule duplication in decision trees, we select multiple rule projection points to accomplish space decomposition. Using simulations of 1,000 to 100,000 rule classifiers, we show that, compared with other existing algorithms, the proposed algorithm achieves an improvement in memory requirement without reducing the search performance.