Enhancing Botnet Detection with AI using LLMs and Similarity Search


As botnets continue to evolve, so do the techniques required to detect them. While Transport Layer Security (TLS) encryption is widely adopted for secure communications, botnets leverage TLS to obscure command-and-control (C2) traffic. These malicious actors often have identifiable characteristics embedded within their TLS certificates, opening a potential pathway for advanced detection techniques.

In first-of-its-kind research, Rapid7’s Dr. Stuart Millar, in collaboration with Kumar Shashwat, Francis Hahn and Prof. Xinming Ou, at the University of South Florida, studied the use of AI large language models (LLMs) to detect botnets’ use of TLS encryption by analyzing embedding similarities to weed out botnets within a sea of benign TLS certificates.

Read more…
Source: Rapid7


Sign up for our Newsletter


Related:

  • Government hackers breached telecom giant Ribbon for months before getting caught

    October 31, 2025

    U.S. telecommunications giant Ribbon has confirmed that government-backed hackers had access to its network for almost a year before getting caught, according to a public filing. The telco giant said in a 10-Q disclosure last week with the U.S. Securities and Exchange Commission that a suspected “nation-state actor had gained access to the company’s IT network” ...

  • UK: Woman charged after around 100 patient records accessed in data breach

    October 31, 2025

    A woman has been charged after around 100 patients had their medical records accessed in a data breach at NHS Lothian. The health board has written letters to patients affected by the breach, which they say was caused by one individual at Edinburgh Royal Infirmary. A letter dated last month, seen by STV News, says the ...

  • Ransomware gang claims Conduent breach: what you should watch for next [updated]

    October 30, 2025

    Updated – October 30, 2025: New information confirms that Conduent’s 2024 breach has impacted over 10.5 million people, based on notifications filed with multiple state attorneys general. The largest disclosure came from the Oregon government, which reported 10.5 million affected residents. Conduent provides technology services to several US state governments, including Medicaid, child support, and food ...

  • Suspected Nation-State Threat Actor Uses New Airstalk Malware in a Supply Chain Attack

    October 29, 2025

    Palo Alto Unit 42 researchers have discovered a new Windows-based malware family they’ve named Airstalk, which is available in both PowerShell and .NET variants. Unit 42 assess with medium confidence that a possible nation-state threat actor used this malware in a likely supply chain attack. The researchers have created the threat activity cluster CL-STA-1009 to identify ...

  • EY exposes 4TB+ SQL database to open internet for who knows how long

    October 29, 2025

    A Dutch cybersecurity outfit says its lead researcher recently stumbled upon a 4TB+ SQL Server backup file belonging to EY exposed to the web, effectively leaking the accounting and consulting megacorp’s secrets. Among the BAK file’s data were API keys, cached authentication tokens, session tokens, service account passwords, and user credentials, Neo Security’s writeup explained. Read more… Source: ...

  • CEO of spyware maker Memento Labs confirms one of its government customers was caught using its malware

    October 28, 2025

    On Monday, researchers at cybersecurity giant Kaspersky published a report identifying a new spyware called Dante that they say targeted Windows victims in Russia and neighboring Belarus. The researchers said the Dante spyware is made by Memento Labs, a Milan-based surveillance tech maker that was formed in 2019 after a new owner acquired and took over ...