Cybersecurity Podcast

Sagamore.ai

Welcome to the Cybersecurity Podcast — your go-to source for all things cyber! Whether you’re a seasoned professional or just diving in, we break down the latest threats, modern attack tactics, cloud security trends, AI-driven defenses, major data breaches, and the future of quantum computing and automation. Each episode is packed with insights, real-world stories, and expert advice to help you stay ahead of the curve. Join our community of learners and defenders as we explore how to secure the digital world — together.

Episodes

  1. New Security Risk: Why LLM Scale Doesn't Deter Backdoor Attacks

    10/12/2025

    New Security Risk: Why LLM Scale Doesn't Deter Backdoor Attacks

    Today, we are discussing a startling finding that fundamentally challenges how we think about protecting large language models (LLMs) from malicious attacks. We’re diving into a joint study released by Anthropic, the UK AI Security Institute, and The Alan Turing Institute. As you know, LLMs like Claude are pretrained on immense amounts of public text from across the internet, including blog posts and personal websites. This creates a significant risk: malicious actors can inject specific text to make a model learn undesirable or dangerous behaviors, a process widely known as poisoning. One major example of this is the introduction of backdoors. These are specific phrases, like the trigger Now, previous research often assumed that attackers needed to control a percentage of the training data. If true, attacking massive, frontier models would require impossibly large volumes of poisoned content. But the largest poisoning investigation to date has found a surprising result. In their experimental setup, they found that poisoning attacks require a near-constant number of documents regardless of model and training data size. This completely challenges the assumption that larger models need proportionally more poisoned data. The key takeaway is alarming: researchers found that as few as 250 malicious documents were sufficient to successfully produce a "backdoor" vulnerability in LLMs ranging from 600 million parameters up to 13 billion parameters—a twenty-fold difference in size. Creating just 250 documents is trivial compared to needing millions, meaning data-poisoning attacks may be far more practical and accessible than previously believed. We’ll break down the technical details, including the specific "denial-of-service" attack they tested, which forces the model to produce random, gibberish text when it encounters the trigger. We will also discuss why these findings favor the development of stronger defenses and what questions remain open for future research. Stay with us as we explore the vital implications of this major security finding on LLM deployment and safety.

    13 min

About

Welcome to the Cybersecurity Podcast — your go-to source for all things cyber! Whether you’re a seasoned professional or just diving in, we break down the latest threats, modern attack tactics, cloud security trends, AI-driven defenses, major data breaches, and the future of quantum computing and automation. Each episode is packed with insights, real-world stories, and expert advice to help you stay ahead of the curve. Join our community of learners and defenders as we explore how to secure the digital world — together.