* update 2023-11-24 06:16:42

arXiv_db/Malware/2023.md

@@ -3228,6 +3228,18 @@
 
 <details>
 
+<summary>2023-11-11 08:38:04 - Progression and Challenges of IoT in Healthcare: A Short Review</summary>
+
+- *S M Atikur Rahman, Sifat Ibtisum, Priya Podder, S. M. Saokat Hossain*
+
+- `2311.12869v1` - [abs](http://arxiv.org/abs/2311.12869v1) - [pdf](http://arxiv.org/pdf/2311.12869v1)
+
+> Smart healthcare, an integral element of connected living, plays a pivotal role in fulfilling a fundamental human need. The burgeoning field of smart healthcare is poised to generate substantial revenue in the foreseeable future. Its multifaceted framework encompasses vital components such as the Internet of Things (IoT), medical sensors, artificial intelligence (AI), edge and cloud computing, as well as next-generation wireless communication technologies. Many research papers discuss smart healthcare and healthcare more broadly. Numerous nations have strategically deployed the Internet of Medical Things (IoMT) alongside other measures to combat the propagation of COVID-19. This combined effort has not only enhanced the safety of frontline healthcare workers but has also augmented the overall efficacy in managing the pandemic, subsequently reducing its impact on human lives and mortality rates. Remarkable strides have been made in both applications and technology within the IoMT domain. However, it is imperative to acknowledge that this technological advancement has introduced certain challenges, particularly in the realm of security. The rapid and extensive adoption of IoMT worldwide has magnified issues related to security and privacy. These encompass a spectrum of concerns, ranging from replay attacks, man-in-the-middle attacks, impersonation, privileged insider threats, remote hijacking, password guessing, and denial of service (DoS) attacks, to malware incursions. In this comprehensive review, we undertake a comparative analysis of existing strategies designed for the detection and prevention of malware in IoT environments.
+
+</details>
+
+<details>
+
 <summary>2023-11-12 17:56:42 - More Than 50% Of The Time, Users Detect Real SMS as Fake: A Smishing Detection Study Of US Population</summary>
 
 - *Daniel Timko, Daniel Hernandez Castillo, Muhammad Lutfor Rahman*
@@ -3310,3 +3322,15 @@
 
 </details>
 
+<details>
+
+<summary>2023-11-22 15:20:12 - Explaining high-dimensional text classifiers</summary>
+
+- *Odelia Melamed, Rich Caruana*
+
+- `2311.13454v1` - [abs](http://arxiv.org/abs/2311.13454v1) - [pdf](http://arxiv.org/pdf/2311.13454v1)
+
+> Explainability has become a valuable tool in the last few years, helping humans better understand AI-guided decisions. However, the classic explainability tools are sometimes quite limited when considering high-dimensional inputs and neural network classifiers. We present a new explainability method using theoretically proven high-dimensional properties in neural network classifiers. We present two usages of it: 1) On the classical sentiment analysis task for the IMDB reviews dataset, and 2) our Malware-Detection task for our PowerShell scripts dataset.
+
+</details>
+