As the machine learning-related technology has made great progress in recent years, deep neural networks are widely used in many scenarios, including security-critical ones, which may incura great loss when DNN is compromised. Starting from introducing several commonly used bit-flip methods, this paper concentrates on bit-flips attacks aiming DNN and the corresponding defense methods. We analyze the threat models, methods design, and effect of attack and defense methods in detail, drawing some helpful conclusions about improving the robustness and resilience of DNN. In addition, we point out several drawbacks to existing works, which can hopefully be researched in the future.

To address the issue of insufficient testing caused by the continuous reduction of software development cycles, many organizations maintain bug repositories and bug tracking systems to ensure real-time updates of bugs. However, each day, a large number of bugs is discovered and sent to the repository, which imposes a heavy workload on bug fixers. Therefore, effective bug deduplication and triage are of great significance in software development. This paper provides a comprehensive investigation and survey of the recent developments in bug deduplication and triage. The study begins by outlining the roadmap of the existing literature, including the research trends, mathematical models, methods, and commonly used datasets in recent years. Subsequently, the paper summarizes the general process of the methods from two perspectives—runtime information-based and bug report-based perspectives—and provides a detailed overview of the methodologies employed in relevant works. Finally, this paper presents a detailed comparison of the experimental results of various works in terms of usage methods, datasets, accuracy, recall rate, and F1 score. Drawing on key findings, such as the need to improve the accuracy of runtime information collection and refine the description information in bug reports, we propose several potential future research directions in the field, such as stack trace enrichment and the combination of new NLP models.

Neural networks have been proven to be vulnerable to adversarial examples; these are examples that can be recognized by both humans and neural networks, although neural networks give incorrect predictions. As an intriguing property of neural networks, adversarial examples pose a serious threat to the secure application of neural networks. In this article, we present another intriguing property of neural networks: the fact that well-trained models believe some examples to be recognizable objects (often with high confidence), while humans cannot recognize such examples. We refer to these as “fooling examples”. Specifically, we take inspiration from the construction of adversarial examples and develop an iterative method for generating fooling examples. The experimental results show that fooling examples can not only be easily generated, with a success rate of nearly 100% in the white-box scenario, but also exhibit strong transferability across different models in the black-box scenario. Tests on the Google Cloud Vision API show that fooling examples can also be recognized by real-world computer vision systems. Our findings reveal a new cognitive deficit of neural networks, and we hope that these potential security threats will be addressed in future neural network applications.

For malware detection, current state-of-the-art research concentrates on machine learning techniques. Binary -gram OpCode features are commonly used for malicious code identification and classification with high accuracy. Binary OpCode modification is much more difficult than modification of image pixels. Traditional adversarial perturbation methods could not be applied on OpCode directly. In this paper, we propose a bidirectional universal adversarial learning method for effective binary OpCode perturbation from both benign and malicious perspectives. Benign features are those OpCodes that represent benign behaviours, while malicious features are OpCodes for malicious behaviours. From a large dataset of benign and malicious binary applications, we select the most significant benign and malicious OpCode features based on the feature SHAP value in the trained machine learning model. We implement an OpCode modification method that insert benign OpCodes into executables as garbage codes without execution and modify malicious OpCodes by equivalent replacement preserving execution semantics. The experimental results show that the benign and malicious OpCode perturbation (BMOP) method could bypass malicious code detection models based on the SVM, XGBoost, and DNN algorithms.

This paper proposes a novel domain-generation-algorithm detection framework based on statistical learning that integrates the detection capabilities of multiple heterogeneous models. The framework includes both traditional machine learning methods based on artificial features and deep learning methods, comprehensively analyzing 34 artificial features and advanced features extracted from deep neural networks. Additionally, the framework evaluates the predictions of the base models based on the fit of the samples to each type of sample set and a predefined significance level. The predictions of the base models are statistically analyzed, and the final decision is made using strategies such as voting, confidence, and credibility. Experimental results demonstrate that the DGA detection framework based on statistical learning achieves a higher detection rate compared to the underlying base models, with accuracy, precision, recall, and F1 scores reaching 0.979, 0.977, 0.981, and 0.979, respectively. The framework also exhibits a stronger adaptability to unknown domains and a certain level of robustness against concept drift attacks.