One Article Review
| Source |  Mandiant |
|---|---|
| Identifiant | 8500392 |
| Date de publication | 2024-04-29 14:00:00 (vue: 2024-05-15 19:06:53) |
| Titre | De l'assistant à l'analyste: la puissance de Gemini 1.5 Pro pour l'analyse des logiciels malveillants From Assistant to Analyst: The Power of Gemini 1.5 Pro for Malware Analysis |
| Texte | Executive Summary A growing amount of malware has naturally increased workloads for defenders and particularly malware analysts, creating a need for improved automation and approaches to dealing with this classic threat. With the recent rise in generative AI tools, we decided to put our own Gemini 1.5 Pro to the test to see how it performed at analyzing malware. By providing code and using a simple prompt, we asked Gemini 1.5 Pro to determine if the file was malicious, and also to provide a list of activities and indicators of compromise. We did this for multiple malware files, testing with both decompiled and disassembled code, and Gemini 1.5 Pro was notably accurate each time, generating summary reports in human-readable language. Gemini 1.5 Pro was even able to make an accurate determination of code that - at the time - was receiving zero detections on VirusTotal. In our testing with other similar gen AI tools, we were required to divide the code into chunks, which led to vague and non-specific outcomes, and affected the overall analysis. Gemini 1.5 Pro, however, processed the entire code in a single pass, and often in about 30 to 40 seconds. Introduction The explosive growth of malware continues to challenge traditional, manual analysis methods, underscoring the urgent need for improved automation and innovative approaches. Generative AI models have become invaluable in some aspects of malware analysis, yet their effectiveness in handling large and complex malware samples has been limited. The introduction of Gemini 1.5 Pro, capable of processing up to 1 million tokens, marks a significant breakthrough. This advancement not only empowers AI to function as a powerful assistant in automating the malware analysis workflow but also significantly scales up the automation of code analysis. By substantially increasing the processing capacity, Gemini 1.5 Pro paves the way for a more adaptive and robust approach to cybersecurity, helping analysts manage the asymmetric volume of threats more effectively and efficiently. Traditional Techniques for Automated Malware Analysis The foundation of automated malware analysis is built on a combination of static and dynamic analysis techniques, both of which play crucial roles in dissecting and understanding malware behavior. Static analysis involves examining the malware without executing it, providing insights into its code structure and unobfuscated logic. Dynamic analysis, on the other hand, involves observing the execution of the malware in a controlled environment to monitor its behavior, regardless of obfuscation. Together, these techniques are leveraged to gain a comprehensive understanding of malware. Parallel to these techniques, AI and machine learning (ML) have increasingly been employed to classify and cluster malware based on behavioral patterns, signatures, and anomalies. These methodologies have ranged from supervised learning, where models are trained on labeled datasets, to unsupervised learning for clustering, which identifies patterns without predefined labels to group similar malware. |
| Envoyé | Oui |
| Condensat | 000 080 189 1917ec456c371778a32bdd74e113b07f33208740327c3cfef268898cbe4efbfe 2017 2022 2023 2024 231 24d004a104d4d54034dbcffc2a4b19a11f39008a575aa614ea04703480b1022c 256 268 280 306 313856 3514368 3723264 445/smb 719b44d93ab39b4fe6113825349addfe5bd411b4d25081916561f9c403599e50 833 853504 |
| Tags | Malware Hack Tool Vulnerability Threat Studies Prediction Cloud Conference |
| Stories | Wannacry |
| Notes | ★★★ |
| Move | 
|
L'article ne semble pas avoir été repris aprés sa publication.
L'article ne semble pas avoir été repris sur un précédent.