Security Mondays with Eva Benn

Eva Benn
  • 0.0 (0)
  • Technology

Cybersecurity is evolving fast and it's hard to keep up amidst all the noise. Host Eva Benn sits down with some of the best global security leaders to talk through what's actually top of mind, the threats they're seeing, the tools they're using, and the calls they're making right now. Every episode gives you practical things you can go do at your organization this week. New episodes every Monday.

  1. 6d ago

    Inside One of the Cruelest Hacks in History | Joe Tidy | S3 E5

    Imagine everything you ever told your therapist sitting on the internet. For roughly 33,000 people in Finland, that happened. The hacker behind the Vastaamo breach did not start out as a nation-state operator. He started as a 12-year-old nuisance in teenage hacking gangs, and a decade later he was blackmailing therapy patients with their own session notes. Joe Tidy has followed that story from the beginning. He is the BBC's first-ever cyber correspondent, and in 2014, as a Sky News reporter, he put that same teenager on air the morning after Lizard Squad knocked PlayStation and Xbox offline over Christmas. His book, Ctrl+Alt+Chaos: How Teenage Hackers Hijack the Internet, traces the gangs, the culture and the police trying to stop them. This year his reporting has moved into AI: the champion ethical hacker who thinks tools like Claude Mythos could put her out of work, and the OpenAI agents that escaped a test environment and hacked Hugging Face. Today we unpack how teenagers actually get from gaming to serious cybercrime, why modern cybercrime is a team sport built on basic social engineering, what to do when a gang tries to recruit one of your employees, what ten years of teen hackers teaches us about containing AI agents, and one thing parents and security leaders can do this week to help break the cycle. ♻️ If this is useful, please share it with your security, engineering, leadership, and insider risk teams. And if you're a parent, share it with the other parents in your life. If the next big breach at your company comes from a 17-year-old on Discord, or an AI agent that won't take no for an answer, is your program built to notice? Hi, I'm Eva Benn. Every Monday morning I bring you the best global security leaders with practical AI security guidance you can turn into action this week. If you have ever found value in this show, please do me a huge favor, drop me a comment, hit the thumbs up on this video and make sure you are subscribed. This tiny action costs you nothing, but it has a huge impact the entire security community, because it helps bring the voices of some of the most incredible leaders in our industry to more people. Every episode is designed to give you practical things you can go and implement in your organization this week. We talked about how teenage hacking gangs disrupt some of the world's biggest companies, and what they teach us about the AI agents now running inside our networks. What you'll walk away with: - How kids get from gaming cheats and Discord servers to serious cybercrime - Why the threat is persistent and social, not "advanced," and what that means for your defenses - What teen hacker behavior tells us about containing autonomous AI agents - How to recognize and respond when a criminal gang tries to recruit one of your employees - One thing parents and security leaders can do this week to keep kids off the dark path If you find this helpful, I'd appreciate a thumbs up, subscribe, and share. It helps more people find the show. Resources we mention in the video: Connect with Joe: - LinkedIn: https://www.linkedin.com/in/joe-tidy-1932764/ - X: https://x.com/joetidy - Ctrl+Alt+Chaos (Elliott & Thompson): https://eandtbooks.com/authors/joe-tidy/ Other resources: - Hugging Face security incident disclosure, July 2026: https://huggingface.co/blog/security-incident-july-2026 - OpenAI, The Hugging Face incident and the road ahead: https://openai.com/index/hugging-face-incident-and-the-road-ahead/ - National Crime Agency, Cyber Choices: https://nationalcrimeagency.gov.uk/cyber-choices - FBI public service announcement on deepfake sextortion: https://www.ic3.gov/PSA/2023/PSA230605 Follow along for more free cybersecurity education. LinkedIn: https://www.linkedin.com/in/evabenn/ Instagram: https://instagram.com/evabennofficial TikTok: https://www.tiktok.com/@evabennofficial Website: https://www.evabenn.com/

  2. Oct 26

    How to Cage AI Agents in the Age of AI Hacking Swarms | Fredrik STÖK | S3 | E4

    Imagine a giant gorilla that has read the entire internet, speaks every language, can plan, decide, and act on its own, and gets stronger every week. Would you cross your fingers it means well and let it run free, or would you put it in a cage? Today we are diving into how to the heck do you cage AI, what does this even mean, why is it important and what you should be doing it now.  Hi, I'm Eva Benn. Every Monday morning I bring you the best global security leaders with practical AI security guidance you can turn into action this week. If you have ever found value in this show, please do me a huge favor, drop me a comment, hit the thumbs up on this video and make sure you are subscribed. This tiny action costs you nothing, but it has a huge impact the entire security community, because it helps bring the voices of some of the most incredible leaders in our industry to more people. Every episode is designed to give you practical things you can go and implement in your organization this week. I was super stoked to chat with Fredrik Alexandersson, who most of you already know as STÖK. He is a Security Solutions Architect at Visma, runs BLKNRTH Security, and co-runs Builders & Breakers with KUGG in Stockholm. He has presented original research on the Black Hat USA Briefings stage twice, and this year Google invited him to Seoul to break its flagship AI products, where he placed second overall and won the Most Creative Report award. Let's just say he knows what he's talking about. Today we unpack what an AI cage actually is and where to start building one, whether an LLM judge can police your agents, where a top AI hacker looks first, what has to change when attackers can run agent swarms cheaply, what monitoring and kill switches look like at scale, and the questions to ask before you say yes to the next team that wants to ship an agent. Connect with STÖK: - LinkedIn: https://www.linkedin.com/in/fredrikalexandersson/ - X: https://x.com/stokfredrik - YouTube: http://www.youtube.com/stokfredrik - Builders & Breakers: https://www.buildersandbreakers.com Resources we mention in the video: STÖK's research, talks and conversations: - AI cages post: https://www.linkedin.com/feed/update/urn:li:activity:7480881913050775552/ - Agentic monitoring open question: https://www.linkedin.com/feed/update/urn:li:activity:7496113414759600128/ - They hacked Google's AI in Seoul (vlog): https://www.youtube.com/watch?v=tJhuAINZWQ0 - Break it, Build it, Ship it, In the Wild with Michael Bargury, ep. 4: https://www.buzzsprout.com/2634323/episodes/19849362-break-it-build-it-ship-it-w-fredrik-stok-alexandersson - Builders & Breakers: Building Hackbots with Hamid Kashfi: https://www.youtube.com/watch?v=MYK9-66qe6w - Builders & Breakers: Local AI for Offensive Security with Thomas Olofsson: https://www.youtube.com/watch?v=xn5mIBaRzWw - Weaponizing Plain Text: ANSI Escape Sequences as a Forensic Nightmare, Black Hat USA 2023: https://i.blackhat.com/BH-US-23/Presentations/US-23-stok-weponizing-plain-text-ansi-escape-sequences-as-a-forensic-nightmare-appendix.pdf Other resources: - Google bugSWAT in Seoul, April 2026: https://bughunters.google.com/blog/bugswat-in-seoul-april-2026 - OWASP Top 10 for LLM Applications 2026: https://genai.owasp.org/resource/owasp-genai-llm-top-10-2026/ - OWASP Agent Control Standard: https://genai.owasp.org/resource/agent-control-standard-acs/ - gVisor: https://gvisor.dev/ - bubblewrap: https://github.com/containers/bubblewrap - Daniel Miessler's LifeOS (formerly PAI): https://github.com/danielmiessler/LifeOS Follow along for more free cybersecurity education. 🤗 LinkedIn: https://www.linkedin.com/in/evabenn/ Instagram: https://www.instagram.com/evabennofficial/ TikTok: https://www.tiktok.com/@evabennofficial Website: https://www.evabenn.com/

  3. Oct 19

    How We Hacked OpenAI with Claude | Zayne Zhang | S3 | E3

    Remember the headlines about the 3 researchers at Hacktron AI who hacked OpenAI through a photo upload? After $3K in Claude tokens and less than 72 hours they had access to OpenAI’s internal code. Today, we’re hearing from Zayne Zhang, co-founder and CEO of Hacktron AI, and we’re going underneath the headlines into how they did it, how the economics of vulnerability exploitation have changed, and most importantly, what you can do about it.  Zayne also ran a live Hacktron pentest for me, and I was blown away by how quickly it found vulnerabilities and demonstrated how they could actually be exploited. Always keeping it practical and useful for you. We don’t kumbaya around here. Before Hacktron, Zayne worked across offensive security, code audits, and penetration testing for global companies, including serving Fortune 20 clients. He also worked in offensive security at TikTok, built security tools at Open Government Products, and served as a cybersecurity specialist at Singapore’s Ministry of Defence during his mandatory military service. As a bug bounty hunter, he reported more than 50 valid security issues to companies around the world. He’s also an angel investor in Pragma and Reading Rhythms. If you're new here, welcome to Security Mondays. Every Monday I bring you some of the most remarkable security leaders in the world with practical AI security guidance you can turn into action this week. If you have ever found value in this show, please do me a huge favor, engage with this post and follow along. This tiny action costs you nothing, but it has a huge impact on the entire security community, because it helps bring the voices of some of the most incredible leaders in our industry to more people. If you find this helpful, I'd appreciate a thumbs up, subscribe, and share. It helps more people find the show. Resources we mention in the video: Connect with Zayne: - X: https://x.com/zeyu1337 - GitHub: https://github.com/zeyu2001 - Website: https://analogue.computer - Hacktron: https://www.hacktron.ai/ - Hacktron on LinkedIn: https://www.linkedin.com/company/hacktron/ Zayne and Hacktron's research: - Hacking OpenAI (full technical write-up): https://www.hacktron.ai/blog/hacking-openai - Here's How an OpenAI Model Went Rogue and Hacked Hugging Face: https://www.hacktron.ai/blog/here-is-how-openai-model-hacked-huggingface - Why Mythos doesn't matter (for us): https://www.hacktron.ai/blog/why-mythos-doesnt-matter-for-us - GLM and DeepSeek Are Catching Frontier Models at Finding Vulnerabilities (the Fider benchmark): https://www.hacktron.ai/blog/open-weight-models-vs-frontier-models - AI hackers are both a generational threat and a generational opportunity (Zayne's May 2025 essay): https://www.hacktron.ai/blog/ai-hackers-generational-threat Other resources: - AI Helps Hackers Hijack OpenAI Staff Accounts Through a Forum, Security Affairs: https://www.securityaffairs.com/199378/ai/ai-helps-hackers-hijack-openai-staff-accounts-through-a-forum.html Follow along for more free cybersecurity education. LinkedIn: https://www.linkedin.com/in/evabenn/ Instagram: https://instagram.com/evabennofficial TikTok: https://www.tiktok.com/@evabennofficial Website: https://www.evabenn.com/

  4. Oct 12

    Farzan Karimi: We Cut Security Reviews From 3 Days to 10 Minutes With AI | S3 | E2

    If you have a hundred findings rated 9.2, which one do you fix first? The score can't tell you. Proof that an attacker can actually exploit it can. Meanwhile AI is flooding security with new tools. Some are real. Some are snake oil. How do you tell the difference, and what should you measure to understand your real exposure? Hi, I'm Eva Benn. Every Monday morning I bring you the best global security leaders with practical AI security guidance you can turn into action this week. If you have ever found value in this show, please do me a huge favor, drop me a comment, hit the thumbs up on this video and make sure you are subscribed. This tiny action costs you nothing, but it has a huge impact the entire security community, because it helps bring the voices of some of the most incredible leaders in our industry to more people. Every episode is designed to give you practical things you can go and implement in your organization this week. I was super stoked to chat with Farzan Karimi, Deputy CISO at Moderna. Farzan has 20+ years in offensive security: he ran the Android red team at Google, was a founding member of the red team at Electronic Arts, and red teamed at Microsoft. At DEF CON 33 he introduced Recursive Request Exploits, nominated for PortSwigger's Top 10 Web Hacking Techniques of 2025, and this summer he scanned 1 million domains and found 2,216 Firebase databases open to the internet. Let's just say he knows what defenders miss. Share this one with your security, AppSec, engineering, and vulnerability management teams. I'm doing my part by bringing you some of the best global leaders in the security industry every Monday, with practical tools and resources you can go use this week. This week, I sat down with Farzan Karimi, Deputy CISO at Moderna. We talked about separating real AI value from snake oil, prioritizing what is actually exploitable, and measuring real exposure instead of counting findings. If AI can now find more vulnerabilities than your team will ever fix, is your program still counting findings, or is it tracking attack paths? Tell me in the comments. If you find this helpful, I'd appreciate a thumbs up, subscribe, and share. It helps more people find the show. Resources we mention in the video: Connect with Farzan: - LinkedIn: https://www.linkedin.com/in/karimi/ - Medium: https://jumpycastle.dev/ - GitHub: https://github.com/jumpycastle Farzan's research and talks: - How I Accessed 1,800 Company Livestreams and Uncovered a New Web Exploit Class: RRE: https://jumpycastle.dev/how-i-accessed-1-800-company-livestreams-and-uncovered-a-new-web-exploit-class-rre-f74b7ef996e7 - RRE Burp Suite extension: https://github.com/jumpycastle/rre-burp - I scanned 1 million domains for Firebase misconfigurations: https://jumpycastle.dev/i-scanned-1-million-domains-for-firebase-misconfigurations-f18c2e0c3f1e - The 20-second Firebase demo (LinkedIn): https://www.linkedin.com/feed/update/urn:li:activity:7472317351636385792/ - Collaboration for battling security incidents, LWN.net report on his SunSecCon 2026 keynote: https://lwn.net/Articles/1063459/ Other resources: - PortSwigger Top 10 Web Hacking Techniques of 2025, nominations list: https://portswigger.net/research/top-10-web-hacking-techniques-of-2025-nominations-open - Inside the race to adapt to an AI-powered security world, CyberScoop: https://cyberscoop.com/ai-powered-cybersecurity-mythos-xbow-agentic-pen-testing/ - XBOW's published Moderna customer story (vendor case study): https://xbow.com/customer-stories/moderna Follow along for more free cybersecurity education. LinkedIn: https://www.linkedin.com/in/evabenn/ Instagram: https://instagram.com/evabennofficial TikTok: https://www.tiktok.com/@evabennofficial Website: https://www.evabenn.com/

  5. Oct 5

    Dave DeWalt: Why Defense in Depth Is No Longer Enough | S3 | EP1

    In 2010, Dave DeWalt was CEO of McAfee when one bad update blue-screened computers across 1,672 companies in just 16 minutes. That was one bad update. Now imagine that same kind of accident in the age of autonomous AI agents, systems that can make decisions and take action across production environments at machine speed. The era of “defense in depth" as we know it is dead. We've officially entered the AI vs. AI era, and what the world needs now is “defense in motion”, security that continuously tests itself, learns from every simulation, and adapts in real time. But what does this actually look in practice? What's the difference between auto-fix and auto-heal? How to separate real innovation from vaporware? These are hard questions, and today we’re tackling them with someone who has helped shape cybersecurity for decades.  I am stoked to premiere Security Mondays Season 3 with the one and only, Dave DeWalt. Dave needs no introduction for most people in cybersecurity, but if you haven't heard of him, he is a 4x CEO (FireEye, McAfee, Documentum) and the Founder and CEO of NightDragon. He has held more than 40 board roles, giving him a rare view into how companies actually make decisions about security, risk and investment. He also sits on the boards of Delta Air Lines and Exelon, and he has advised U.S. administrations through NSTAC and CISAs Cybersecurity Advisory Committee.  If you're new here, hi and welcome to Security Mondays. Every Monday I bring you some of the most remarkable global security leaders with practical AI security guidance you can turn into action this week.  If you find this helpful, please do me a huge favor, give us a thumbs up, subscribe, and share. It costs you nothing, but it makes a huge difference for the entire security community, because collective defense only works when we share what we know. Resources we mention in the video: Connect with Dave: - LinkedIn: https://www.linkedin.com/in/ddewalt/ - NightDragon bio: https://www.nightdragon.com/company/team/dave-dewalt/ - NightDragon: https://www.nightdragon.com/ - Horizon3.ai NodeZero (autonomous pen testing): https://horizon3.ai/nodezero/ - Horizon3.ai $250M Series E announcement: https://horizon3.ai/news/press-release/horizon3-raises-250m-series-e-at-2b-valuation-to-lead-the-ai-vs-ai-cybersecurity-era/ - NightDragon Market Report: Autonomous Defense: https://www.nightdragon.com/insights/research/nightdragon-market-report-autonomous-defense/ - CyberScoop: "AI is separating the companies built to scale from the ones built to sell": https://cyberscoop.com/ai-cybersecurity-market-trends-2026-op-ed/ Chapters 00:00 – Intro 03:29 – Is Cybersecurity Still in a Dark Period? 05:53 – The Rise of the Agent State 09:16 – Why NightDragon Made a Bigger Bet on Horizon3.ai 12:21 – Auto-Fix vs Auto-Heal: Lessons From the 2010 McAfee Outage 14:58 – Defense in Motion and Scaling the SOC With Agents 17:45 – How to Trust an Autonomous Security Platform 20:05 – Measuring Risk in 2026: Always-On Red and Blue Teams 22:16 – Autonomy as the Sixth Domain of Defense 25:03 – The Four Ts: Spotting Real Companies vs Vaporware 28:03 – 2027 Budgets: The 70 Vendors You May Not Need And follow along for more free cybersecurity education. 🤗 LinkedIn: https://www.linkedin.com/in/evabenn/ Instagram: https://www.instagram.com/evabennofficial/ TikTok: https://www.tiktok.com/@evabennofficial Website: https://www.evabenn.com/

  6. Sep 21

    10 Cybersecurity Leaders: 5 Hard Truths About AI (And Your Action Plan)

    If you watch one video from Season 2 of Security Mondays, make it this one.10 episodes. Some of the most respected names in cybersecurity. Five themes that kept coming up again and again. I boiled it all down to under 15 minutes, so you can walk away with guidance you can use THIS week.Season 2 is officially a wrap. I got to sit down with leaders from completely different backgrounds, with completely different experiences. And they kept landing on the same five lessons. That's not a coincidence.A huge thank you to the incredible guests who made Season 2 possible:Rob Lee: AI security, cybersecurity fundamentals, and how AI is changing the speed of security.Thomas Rocha: AI threat intelligence and how the threats are changing.Helen Oakley & Dimitri Raidman: AI supply chain security and the risks hiding across the AI stack.Neil Provost: Security invariance, and building security that holds up as environments change.Joshua Copeland: Security theater, and why having a control is NOT the same as proving it works.Heath Adams: The attacker mindset, and thinking like the people trying to break your systems.Josh Bressers: The future of open source and the security challenges it faces.Tim Raines: AI aerospace strategy and the security implications of AI in critical environments.Rob Joyce: Offensive operations, national security, and lessons from decades in the field.Every conversation pointed to the same thing:AI is exposing every weak spot in the security playbook we already had, at a speed and scale we can no longer ignore.The five themes:1. AI changed the speed, not the fundamentals.2. Know what you have and what it can access.3. Assume agents will fail and contain the blast radius.4. Stop believing your security works. Test it.5. Finding vulnerabilities is getting cheap. Fixing them is the hard part.But HOW do you actually use any of this on Monday morning?Don't try to do everything at once. Pick ONE lesson. Put it into practice this week.That's how we roll here.Thank you for watching, commenting, and sharing these episodes with your teams. You made Season 2 what it was, and it has meant the world to me. ❤️Season 3 is coming soon, and we're kicking it off with Dave DeWalt on October 5th. Until then, I'll be here every Monday with practical AI security guidance you can turn into action.Which of the five themes hits closest to home for your team? Tell me in the comments 👇If you enjoyed this episode, I'd really appreciate a subscribe and a thumbs up.Follow along for more free cybersecurity education. 🤗---Want to hear from more voices in AI security? Security Mondays is a proud partner and supporter of the AI Cyber Magazine. Find it in any Lufthansa or Delta lounges. Not traveling soon? Get your copy here: https://aicybermagazine.comFollow along for more free cybersecurity education. 🤗LinkedIn: https://www.linkedin.com/in/evabenn/Instagram: https://www.instagram.com/evabennofficial/TikTok: https://www.tiktok.com/@evabennofficialWebsite: https://www.evabenn.com/

  7. Sep 14

    Ex-NSA Hacker Chief: The REAL Reason Hackers Get In | Rob Joyce | S2 E9

    Hi, I'm Eva Benn. Every Monday morning I bring you some of the best global security leaders to talk through what's actually top of mind, the threats they're seeing, the tools they're using, and the decisions they're making right now. Every episode is designed to give you practical things you can go and implement in your organization this week.This week, I sat down with Rob Joyce, former Director of Cybersecurity at the National Security Agency and founder of Joyce Cyber. We talked about what changed once AI agents could run most of an attack on their own, and the concrete moves a security leader can make this week to keep pace. What you'll walk away with: - What still stops a top-tier attacker, and the one defense to add now. - What changed in AI-enabled offense, and the assumption to drop from your threat model. - How to check if you qualify for the NSA's free cyber services and sign up this week. - The identity audit to run today: phishing-resistant MFA and killing stale accounts. - The one thing to start Monday, and how to know by Friday that you moved. If you find this helpful, I'd appreciate a thumbs up, subscribe, and share. It helps more people find the show. Connect with Rob: LinkedIn: https://www.linkedin.com/in/rob-joyce-b43445116/ ResourcesUSENIX Enigma 2016 — "Disrupting Nation State Hackers" (talk): https://www.youtube.com/watch?v=bDJb8WOJYdA USENIX Enigma 2016 talk page + transcript: https://www.usenix.org/conference/enigma2016/conference-program/presentation/joyce NSA Cybersecurity Collaboration Center (free services, eligibility): https://www.nsa.gov/ccc Anthropic — "Disrupting the first reported AI-orchestrated cyber espionage campaign" (Nov 2025): https://www.anthropic.com/news/disrupting-AI-espionage Rob Joyce at the Secureframe National Cybersecurity Summit (six moves; AI offense): https://secureframe.com/blog/rob-joyce-dib-cybersecurity Rob Joyce testimony, House Select Committee on the CCP (Mar 5, 2025): https://docs.house.gov/meetings/ZS/ZS00/20250305/117983/HHRG-119-ZS00-Wstate-JoyceR-20250305.pdf XBOW tops HackerOne (2025): https://xbow.com/blog/xbow-on-hackerone-whats-next Chapters:00:00 — Why Hackers Don't Care Who You Are Anymore05:18 — AI Just Changed the Economics of Hacking07:55 — Why Every Organization Is Now a Potential Target10:15 — The Three Defenses You Can't Afford to Ignore17:04 — When AI Agents Become the New Insider Threat20:07 — Why Attackers Can Now Outpace Your Patch Cycle30:01 — The Cryptography Deadline Security Leaders Can't IgnoreWant to hear from more voices in AI security? Security Mondays is a proud partner and supporter of the AI Cyber Magazine. Find it in any Lufthansa or Delta lounges. Not traveling soon? Get your copy here: https://aicybermagazine.comAnd follow along for more free cybersecurity education. 🤗LinkedIn: https://www.linkedin.com/in/evabenn/Instagram: https://www.instagram.com/evabennofficial/TikTok: https://www.tiktok.com/@evabennofficialWebsite: https://www.evabenn.com/

  8. Sep 7

    CISO with 30+ Years in Cyber: How to Adapt Your Security Strategy for AI | Tim Rains | S2 E8

    Hi, I'm Eva Benn. Every Monday morning I bring you some of the best global security leaders to talk through what's actually top of mind, the threats they're seeing, the tools they're using, and the decisions they're making right now. Every episode is designed to give you practical things you can go and implement in your organization this week.Every week there's a new AI security product and a new reason to panic. This episode is the opposite of that. Tim Rains has spent his career figuring out how organizations actually get compromised and which strategies actually hold up, and his take on AI is refreshingly calm: most of what works still works, and the real skill is knowing which few parts of your program AI genuinely breaks.I'm doing my part by bringing you some of the best global leaders in the security industry every Monday, with practical tools and resources you can go use this week.What you'll walk away with:- A clear sense of which parts of your strategy to revisit for AI, and which to leave alone- Where to double down on fundamentals versus where to fund something new- A 90-day change for vulnerability management when discovery and exploitation move at machine speed- The security requirements to set before an AI system reaches production- A way to tier AI use cases by consequence and decide how much autonomy each getsConnect with Tim:- LinkedIn: https://www.linkedin.com/in/timrains/Tim's book:- Cybersecurity Strategy for the AI-Driven Era, 3rd ed. (Packt): https://www.packtpub.com/en-us/product/cybersecurity-strategy-for-the-ai-driven-era-9781806028573- Amazon: https://www.amazon.com/Cybersecurity-Strategy-AI-Driven-Era-data-driven/dp/1806028573Resources we talked about- Tim on securing AI agents (Okta Executive Exchange): https://www.okta.com/newsroom/articles/adt-ciso-tim-rains-on-why-ai-agent-access-is-crucial-and-risky/- OpenAI–Hugging Face incident, Black Hat 2026 (SC Media): https://www.scworld.com/news/black-hat-2026-openai-reveals-agents-planned-collective-attacks-via-secret-message-board- MITRE ATT&CK: https://attack.mitre.org/- CWE-20, Improper Input Validation (MITRE): https://cwe.mitre.org/data/definitions/20.html- OWASP API Security Top 10: https://owasp.org/API-Security/Chapters00:00 — The AI Shift Every Security Leader Needs to Prepare For03:03 — The Three Security Priorities AI Changes First07:35 — Why AI Can't Be a Separate Security Strategy09:40 — Where Security Budgets Should Go Now13:15 — Why Vulnerability Scanning Is No Longer Enough20:21 — How to Secure AI When Input Can't Be Trusted23:32 — Why AI Autonomy Could Multiply Your RiskFollow along for more free cybersecurity education. 🤗LinkedIn: https://www.linkedin.com/in/evabenn/Instagram: https://www.instagram.com/evabennofficial/TikTok: https://www.tiktok.com/@evabennofficialWebsite: https://www.evabenn.com/

See All (26)

About

Cybersecurity is evolving fast and it's hard to keep up amidst all the noise. Host Eva Benn sits down with some of the best global security leaders to talk through what's actually top of mind, the threats they're seeing, the tools they're using, and the calls they're making right now. Every episode gives you practical things you can go do at your organization this week. New episodes every Monday.

Information

You Might Also Like