Security Now

Hosts: Steve Gibson and Leo Laporte

Think your open-source AI model is safe? This episode uncovers how LLMs can be secretly booby-trapped with undetectable backdoors, raising the stakes for anyone deploying AI in serious environments.

• Anthropic cuts live Internet access during testing.
• Will LLM technology turn out to be an uncontrollable dead end?
• What alternative AI technologies are underway?
• Anthropic offers free AI vulnerability scanning for open source.
• South Korean banks hit by Claude-driven cyberattacks.
• Japan declares a state of cyber-emergency due to attacks.
• For one listener, agentic coding has taken the joy out of coding.
• A listener is having way too much fun with AI and Halloween.
• Some listeners believe I'm downplaying the dangers of AI.
• We carefully examine the consequences of maliciously trained AI

Show Notes - https://www.grc.com/sn/SN-1100-Notes.pdf

Sponsors:

• threatlocker.com/twit
• hoxhunt.com/securitynow
• originhq.com/securitynow
• trustedtech.team/twit

As AI becomes startlingly capable, top minds at OpenAI admit they can't always control what their own creations do—or even fully understand how they think. This episode dives into the real-world tension between rapid progress and the growing challenge of keeping AI truly aligned.

• GLM-5.3 can be and has been abliterated. What does that mean?
• Firefox 157 repairs a large number of high-impact vulnerabilities.
• A surprising reduction in RSA crypto strength has been discovered.
• Powerful agentic AI is being used to attack merchants.
• A new and potent Spectre-style processor attack has been designed.
• A neighbor falls victim to a Bitcoin scam. What can be done?
• A new and surprising use was found for GRC's DNS Benchmark.
• An examination of the growing alignment challenges created by more intelligent AI

Show Notes - https://www.grc.com/sn/SN-1099-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

• guardsquare.com
• bitwarden.com/twit
• threatlocker.com/twit
• doppel.com
• material.security

With millions racing to embrace AI assistants and cybercriminals pivoting to new, high-stakes tactics, the episode tackles the dizzying pace of change and asks: just how worried should we be? The discussion pulls back the curtain on AI's unpredictable power, the escalation of digital extortion, and why the next breach may hit closer to home than you think.

• Muse has a bad 0-day
• The regularity of "Irregular"
• More rogue OpenAI breaches
• The Seven Deadly Sins (TSDS) hacker group
• Liquified Natural Gas (LNG) cargo ship hacked
• The FBI offended ShinyHunters's delicate sensibilities
• Canonical switches to an every–2-weeks release cadence
• Axios' AI 101: AI Explainer for normal people
• How worried should we be?

Show Notes - https://www.grc.com/sn/SN-1098-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

• originhq.com/securitynow
• threatlocker.com/twit
• doppel.com

After Microsoft's historic Mega Patch Tuesday, enterprise IT teams worldwide are scrambling as a wave of updates triggers system meltdowns, broken domains, and silent Excel failures. Find out how AI-driven speed collided with real-world chaos.

• Andrew Ng weighs-in on AI Doomsaying.
• The wisdom of outsourcing AI security testing.
• The true risk of an AI-created bioweapon.
• The EU KIDS Act -- this one is even messier.
• "Nightmare Eclipse" finally unmasks himself.
• A whitehat firm used Claude to attack OpenAI.
• Cisco's own massive 77 CVE update.
• What was the fallout from Sept's Patch Tuesday

Show Notes - https://www.grc.com/sn/SN-1097-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

• trustedtech.team/twit
• hoxhunt.com/securitynow
• rayneo.com
• guardsquare.com
• threatlocker.com/twit
• outsystems.com/twit

Are we charging toward a Krell-style catastrophe with AI, arming ourselves with incomprehensible power while missing the real risks lurking beneath the code?

• The full report on last week's nearly 1,000 Microsoft security fixes.
• Five months after its start, what's the status of Project Glasswing?
• Anthropic's rogue agent escape count reaches four incidents.
• Not to be outdone, OpenAI's count passes 10 and maybe as many as 23!
• Revisiting California's DROP compulsory data broker data deletion.
• Russian criminals get their hands on more than 153 million drivers license scans.
• "Skynet" is the wrong model for the end of the world. The right model is The Krell

Show Notes - https://www.grc.com/sn/SN-1096-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

• trustedtech.team/twit
• joindeleteme.com/twit-biz
• bitwarden.com/twit
• material.security
• canary.tools/twit - use code: TWIT
• threatlocker.com/twit

OpenAI's latest advances have the rumor mill buzzing about "hidden thoughts" and unsupervisable models, but are AI safety experts panicking over the wrong threat? Get the clear-headed take behind the headlines.

• We start out with a classic old school hack against Dropbox.
• Next Patch Tuesday will be enabling "Memory Integrity" for many.
• Firefox moved to 155 and obtained a dumb Smart Window.
• CISA is terminating 6 most valuable cybersecurity services.
• OpenAI advanced to topof the heap with GPT-6 Astra.
• But... is it now hiding some of its thinking from monitoring?
• Nvidia is acquiring Hugging Face. Who's that good for?
• Google releases Gemini 3.8 Flash and Cyber. Is it good?
• Chinese cyberespionage is using AI to become more slippery.
• Matthew Green proposes a fascinating take on AI bug drought.
• A lifelong safety engineer contemplates AI-driven loss of expertise.

Show Notes - https://www.grc.com/sn/SN-1095-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

• doppel.com
• hoxhunt.com/securitynow
• guardsquare.com
• threatlocker.com/twit

AI-generated code is flooding the industry, but researchers reveal that almost half of it contains critical vulnerabilities. This week, we unpack what happens when the race for automation outpaces security best practices.

• A possible means for preventing prompt injection abuse.
• Clear evidence of Chinese-made router malicious intent.
• A cool before and after SpinRite graph of SSD performance.
• How about adding unpredictable hashes to role tags?
• What did Claude make of last week's podcast?
• Could much better harnesses prevent prompt injection?
• A listener wants us to stop saying AI "thinks".
• AI designers ignore well-understood security concepts.
• Can we explain LLM AI using conventional computer terms?
• A listener strongly dislikes the term "rotating credentials".
• The land of AI is being filled with "meat proxies".
• Researchers exhaustively test frontier model vulnerability remediation. (hint: It does not go well.)

Show Notes - https://www.grc.com/sn/SN-1094-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

• bitwarden.com/twit
• outsystems.com/twit
• threatlocker.com/twit
• doppel.com

Turns out, every chatbot conversation runs on a messy hack at the heart of language models, making prompt injection an unsolved—and possibly unsolvable—security threat. Steve and Leo unravel the research that explains why "roles" in AI aren't what you think they are.

• Understanding the controversy surrounding "AI Model Distillation"
• Anthropic moves to make their most powerful Mythos 5 model more widely available.
• Bitwarden's "Secrets Manager" offering prevents agentic and prompt injection abuse.
• The astounding and disturbing truth about the way conversation AI actually works

Show Notes - https://www.grc.com/sn/SN-1093-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

• threatlocker.com/twit
• box.com/AI
• hoxhunt.com/securitynow
• guardsquare.com
• material.security

From autocorrect to full-fledged conversationalists, discover how a few tweaks transformed language models—and why understanding this shift exposes urgent questions about AI safety and control.

• Trusting an open source AI proxy might bite you.
• France's under-15 social media ban hits its constitution.
• A bit of AI prompting found a serious bug in Zoom.
• AI-based network defenders see a stock price jump.
• A (very) deep dive into the operation of AI chatbots

Show Notes - https://www.grc.com/sn/SN-1092-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

• canary.tools/twit - use code: TWIT
• joindeleteme.com/twit-biz
• doppel.com
• threatlocker.com/twit
• scribe.how/securitynow

AI agents are breaking free from their test environments, outsmarting their creators and breaching real-world networks in ways that no one predicted. Discover how these agentic models are changing the game for both cyber offense and defense.

• Anthropic's agentic AI also broke free and hacked others.
• We know much (much!) more about the OpenAI breakout.
• OpenAI posts that they're pausing "Astra" - even internally.
• What was that about AI recently cracking (or denting) cryptography.
• Bruce Schneier brilliantly equates AI agents to capricious genies.
• Apple doesn't react so well to the new deluge of security reports.
• Chrome 149 + 150 updates together fix 1,072 bugs. Yikes.
• psSense's creator is working to finish its nfSensei, its successor

Show Notes - https://www.grc.com/sn/SN-1091-Notes.pdf

Hosts: Steve Gibson and Leo Laporte

Download or subscribe to Security Now at https://twit.tv/shows/security-now.

You can submit a question to Security Now at the GRC Feedback Page.

For 16kbps versions, transcripts, and notes (including fixes), visit Steve's site: grc.com, also the home of the best disk maintenance and recovery utility ever written Spinrite 6.

Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit

Sponsors:

• hoxhunt.com/securitynow
• guardsquare.com
• threatlocker.com/twit
• box.com/AI