Google uses LLMs and LoRA to combat AI-generated spam networks

Google researchers have developed a new system called Scalable Cluster Termination System (S-CTS) to combat AI-generated spam on video platforms. This multimodal defense mechanism uses Large Language Models (LLMs) enhanced with LoRA and APO to detect and terminate coordinated botnets. The system shifts focus from individual content moderation to identifying clusters of accounts exhibiting synchronized, inorganic behavior and analyzing content for subtle generative artifacts. AI

IMPACT This system could significantly improve content moderation on video platforms, reducing the spread of misinformation and scam content.

RANK_REASON The article describes a system developed by Google to combat AI-generated spam, which is a tool or product rather than a frontier release, research paper, or significant industry event.

Read on dev.to — LLM tag →

• Abhinav Mathur
• Claire Liu
• Google
• Kelvin Tan
• LLMs
• LoRA
• Scalable Cluster Termination System (S-CTS)
• Yifei Liu

• product
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →