<![CDATA[Threat Bytes]]>Here we go beyond the headlines to explore what modern cyber threats actually look like.

Through candid conversations with security leaders, researchers, practitioners, and people who have experienced cyberattacks firsthand, we uncover the stories, decisions, behaviors, and lessons behind today's evolving threat landscape.

From real world attacks and emerging technologies to AI driven threats and the challenges security leaders face every day, each episode explores one compelling question and gets beneath the surface of what happened, why it matters, and what we can learn from it.

Threat Bytes is not about product pitches or technical tutorials. It is about honest conversations, real experiences, and perspectives that help make sense of an increasingly complex cybersecurity world.

]]>www.Radware.comRiverside.fm (https://riverside.com)Mon, 02 Nov 2026 07:39:44 GMTThu, 25 Jun 2026 08:44:53 GMT60Radware<p><b><strong>Here we go beyond the headlines to explore what modern cyber threats actually look like.</strong></b></p><p>Through candid conversations with security leaders, researchers, practitioners, and people who have experienced cyberattacks firsthand, we uncover the stories, decisions, behaviors, and lessons behind today's evolving threat landscape.</p><p>From real world attacks and emerging technologies to AI driven threats and the challenges security leaders face every day, each episode explores one compelling question and gets beneath the surface of what happened, why it matters, and what we can learn from it.</p><p>Threat Bytes is not about product pitches or technical tutorials. It is about honest conversations, real experiences, and perspectives that help make sense of an increasingly complex cybersecurity world.</p>episodicRadwareevatldn@gmail.comno<![CDATA[Runaway Agents: When AI Stops Following the Rules]]>What happens when agents go beyond its task, its guardrails, or the environment it was supposed to stay inside?

In this episode, host Eva Abergel talks with Pascal Geenens, Vice President of Cyber Threat Intelligence at Radware, about what it really means when an AI agent "escapes." It starts with a gym story and moves quickly to the incidents that put the security community on alert. These include the Hugging Face case, experiments by the UK AI Security Institute, and containment issues reported by Anthropic and OpenAI

These weren't only researchers testing models, though. Pascal explains how malicious actors are already weaponizing AI agents.

The more an agent can do, the more it matters to know what it can access, who is watching, and where the boundaries really are.

]]>https://www.radware.com/a087549b-3d20-4e48-b218-669b5ec43805Sun, 25 Oct 2026 10:43:05 GMT<p>What happens when agents go beyond its task, its guardrails, or the environment it was supposed to stay inside?</p><p>In this episode, host Eva Abergel talks with Pascal Geenens, Vice President of Cyber Threat Intelligence at Radware, about what it really means when an AI agent "escapes." It starts with a gym story and moves quickly to the incidents that put the security community on alert. These include the Hugging Face case, experiments by the UK AI Security Institute, and containment issues reported by Anthropic and OpenAI </p><p>These weren't only researchers testing models, though. Pascal explains how malicious actors are already weaponizing AI agents. </p><p>The more an agent can do, the more it matters to know what it can access, who is watching, and where the boundaries really are.</p>no00:26:151Runaway Agents: When AI Stops Following the Rulesfull