* update 2024-02-06 06:18:06

arXiv_db/Malware/2024.md

@@ -3,6 +3,7 @@
 ## TOC
 
 - [2024-01](#2024-01)
+- [2024-02](#2024-02)
 
 ## 2024-01
 
@@ -234,3 +235,30 @@
 
 </details>
 
+
+## 2024-02
+
+<details>
+
+<summary>2024-02-01 20:54:41 - algoXSSF: Detection and analysis of cross-site request forgery (XSRF) and cross-site scripting (XSS) attacks via Machine learning algorithms</summary>
+
+- *Naresh Kshetri, Dilip Kumar, James Hutson, Navneet Kaur, Omar Faruq Osama*
+
+- `2402.01012v1` - [abs](http://arxiv.org/abs/2402.01012v1) - [pdf](http://arxiv.org/pdf/2402.01012v1)
+
+> The global rise of online users and online devices has ultimately given rise to the global internet population apart from several cybercrimes and cyberattacks. The combination of emerging new technology and powerful algorithms (of Artificial Intelligence, Deep Learning, and Machine Learning) is needed to counter defense web security including attacks on several search engines and websites. The unprecedented increase rate of cybercrime and website attacks urged for new technology consideration to protect data and information online. There have been recent and continuous cyberattacks on websites, web domains with ongoing data breaches including - GitHub account hack, data leaks on Twitter, malware in WordPress plugins, vulnerability in Tomcat server to name just a few. We have investigated with an in-depth study apart from the detection and analysis of two major cyberattacks (although there are many more types): cross-site request forgery (XSRF) and cross-site scripting (XSS) attacks. The easy identification of cyber trends and patterns with continuous improvement is possible within the edge of machine learning and AI algorithms. The use of machine learning algorithms would be extremely helpful to counter (apart from detection) the XSRF and XSS attacks. We have developed the algorithm and cyber defense framework - algoXSSF with machine learning algorithms embedded to combat malicious attacks (including Man-in-the-Middle attacks) on websites for detection and analysis.
+
+</details>
+
+<details>
+
+<summary>2024-02-02 12:27:32 - TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time (Extended Version)</summary>
+
+- *Zeliang Kan, Shae McFadden, Daniel Arp, Feargus Pendlebury, Roberto Jordaney, Johannes Kinder, Fabio Pierazzi, Lorenzo Cavallaro*
+
+- `2402.01359v1` - [abs](http://arxiv.org/abs/2402.01359v1) - [pdf](http://arxiv.org/pdf/2402.01359v1)
+
+> Machine learning (ML) plays a pivotal role in detecting malicious software. Despite the high F1-scores reported in numerous studies reaching upwards of 0.99, the issue is not completely solved. Malware detectors often experience performance decay due to constantly evolving operating systems and attack methods, which can render previously learned knowledge insufficient for accurate decision-making on new inputs. This paper argues that commonly reported results are inflated due to two pervasive sources of experimental bias in the detection task: spatial bias caused by data distributions that are not representative of a real-world deployment; and temporal bias caused by incorrect time splits of data, leading to unrealistic configurations. To address these biases, we introduce a set of constraints for fair experiment design, and propose a new metric, AUT, for classifier robustness in real-world settings. We additionally propose an algorithm designed to tune training data to enhance classifier performance. Finally, we present TESSERACT, an open-source framework for realistic classifier comparison. Our evaluation encompasses both traditional ML and deep learning methods, examining published works on an extensive Android dataset with 259,230 samples over a five-year span. Additionally, we conduct case studies in the Windows PE and PDF domains. Our findings identify the existence of biases in previous studies and reveal that significant performance enhancements are possible through appropriate, periodic tuning. We explore how mitigation strategies may support in achieving a more stable and better performance over time by employing multiple strategies to delay performance decay.
+
+</details>
+