AI & security · Archive

AI & security

Dates are publishers’ publication dates, source update dates, or CISA catalog-added dates. First collected records when SecSIG first saw the entry.

• OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication ↗ (opens in a new tab)

  The Hacker News · Published 2026-10-25 · First collected 2026-10-25

• Autonomous attack agent in 'Skynet mode' hijacks other models to carry out its evil deeds ↗ (opens in a new tab)

  NCSC Finland Daily Security News · Published 2026-10-25 · First collected 2026-10-25

• The PHP Meltdown Shows How AI Makes Bugs More Exploitable ↗ (opens in a new tab)

  WIRED Security · Published 2026-10-24 · First collected 2026-10-24

• Three insights you may have missed from theCUBE’s coverage of Oracle’s “AI Cyberattacks Are Escalating: How to Secure Your Data Now” virtual event ↗ (opens in a new tab)

  Security - SiliconANGLE · Published 2026-10-23 · First collected 2026-10-24

• Enterprises face evolving insurance landscape for artificial intelligence risks ↗ (opens in a new tab)

  SC Media · Published 2026-10-23 · First collected 2026-10-24

• New Evidence Shows LiteLLM Secret-Stealing Workflows Ran 11 Days Before Supply Chain Attack ↗ (opens in a new tab)

  Socket · Published 2026-10-23 · First collected 2026-10-24

• Microsoft Teams to get AI-powered, context-aware phishing detection ↗ (opens in a new tab)

  BleepingComputer · Published 2026-10-23 · First collected 2026-10-24

• Inside the LiteLLM 1.107.0 supply chain compromise: Credential theft through Python startup hooks ↗ (opens in a new tab)

  Microsoft Security Blog · Published 2026-10-23 · First collected 2026-10-24

• AI token abuse: What it is and how to prevent it ↗ (opens in a new tab)

  Fingerprint Blog RSS Feed · Published 2026-10-23 · First collected 2026-10-24

• Artificial Intelligence and Reverse Engineering: Defeating DoNex by Automating Analysis with REA and MCP Protocol ↗ (opens in a new tab)

  Secjuice · Published 2026-10-23 · First collected 2026-10-24

• AI Tools Are Generating Massive Attacks for Little Cost ↗ (opens in a new tab)

  darkreading · Published 2026-10-23 · First collected 2026-10-24

• Podcast: ‘Reverse-Engineer Anything’ Is the Next Wave of AI Slop ↗ (opens in a new tab)

  404 Media · Published 2026-10-23 · First collected 2026-10-24

• Built-In Weakness: Lawful Access and Encryption in the Age of AI-Powered Cyber Threats ↗ (opens in a new tab)

  The Citizen Lab · Published 2026-10-23 · First collected 2026-10-24

• 1Password Lets AI Agents Log In Without Seeing Your Passwords ↗ (opens in a new tab)

  eSecurity Planet · Published 2026-10-23 · First collected 2026-10-24

• U.S. Banks Detect Unauthorized AI Agents Accessing Accounts ↗ (opens in a new tab)

  Security Magazine · Published 2026-10-23 · First collected 2026-10-24

• In Other News: Tor Exit Relays Hijacked, Banks Spot Rogue AI Agents, Self-Rebuilding macOS Ransomware ↗ (opens in a new tab)

  SecurityWeek · Published 2026-10-23 · First collected 2026-10-24

• Infostealer riding the AI Train ↗ (opens in a new tab)

  Check Point Research · Published 2026-10-23 · First collected 2026-10-24

• Cybercrime Is The World’s Third-Largest Economy. AI Attacks And Defends. ↗ (opens in a new tab)

  Cybercrime Magazine · Published 2026-10-23 · First collected 2026-10-24

• Microsoft Frontier Tour London: Agentic AI governance in the spotlight ↗ (opens in a new tab)

  ComputerWeekly.com · Published 2026-10-23 · First collected 2026-10-24

• 88% of UK firms have had an 'agentic security incident' in the last year ↗ (opens in a new tab)

  Latest from ITPro in Security · Published 2026-10-23 · First collected 2026-10-24

• The AI notetaker risk is now an everywhere problem ↗ (opens in a new tab)

  CSO Online · Published 2026-10-23 · First collected 2026-10-24

• Why Organizations Secure AI Agents with Falcon Guardian ↗ (opens in a new tab)

  CrowdStrike Blog · Published 2026-10-23 · First collected 2026-10-24

• AI Hype, PHP and the Illusion of Expertise in Tech Journalism ↗ (opens in a new tab)

  HackerNoon - cybersecurity · Published 2026-10-23 · First collected 2026-10-24

• MetaDefender™ Cluster 2.10.0 Brings URL-Based Scanning, Expanded Archive Reuse, and OPSWAT AI Deflection Engine ↗ (opens in a new tab)

  OPSWAT Blog · Published 2026-10-22 · First collected 2026-10-24

• ASPM in the AI Era Part 2: Prioritize Exploitable Risks with Code-to-Cloud Context ↗ (opens in a new tab)

  Wiz Blog | RSS feed · Published 2026-10-22 · First collected 2026-10-24

• 53% vs.19%: The budget divide separating AI leaders from everyone else ↗ (opens in a new tab)

  iTnews · Published 2026-10-22 · First collected 2026-10-24

• Zoomtopia 2026: Zoom Introduces AI Agents, New Security Controls ↗ (opens in a new tab)

  Security Archives - TechRepublic · Published 2026-10-22 · First collected 2026-10-24

• Microsoft Links ConnectWise Breach to China-Linked Group Using AI Pentesting Tool ARTEX ↗ (opens in a new tab)

  Security Affairs · Published 2026-10-22 · First collected 2026-10-24

• Memory Safety, AI security, Auth Challenges - BTS #84 ↗ (opens in a new tab)

  Eclypsium | Supply Chain Security for the Modern Enterprise · Published 2026-10-22 · First collected 2026-10-24

• The Guardian view on AI safety: the push for global regulation must advance | Editorial ↗ (opens in a new tab)

  Data and computer security | The Guardian · Published 2026-10-22 · First collected 2026-10-24