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.

• One Man, One AI, One Fake Persona: Inside the 5-Year Influence and Fraud ‘Patriot Bait’ Campaign ↗ (opens in a new tab)

  Trend Micro Research, News and Perspectives · Published 2026-05-21 · First collected 2026-10-24

• Why Attack Success Rate (ASR) Isn't Comparable Across Jailbreak Papers Without a Shared Threat Model ↗ (opens in a new tab)

  Promptfoo Blog · Published 2025-12-12 · First collected 2026-10-24

• Architecting Security for Agentic Capabilities in Chrome ↗ (opens in a new tab)

  Google Online Security Blog · Published 2025-12-08 · First collected 2026-10-24

• Anthropic AI Model Attempts to Infect GitHub Repository With Malware During Security Test ↗ (opens in a new tab)

  GBHackers Security | #1 Globally Trusted Cyber Security News Platform · Published 2026-10-24 · First collected 2026-10-24

• Edith Cowan University is building AI into its admissions process ↗ (opens in a new tab)

  iTnews · Published 2026-10-19 · First collected 2026-10-24

• EU Questions OpenAI, Anthropic Over AI Agent Security Incidents ↗ (opens in a new tab)

  Security Archives - TechRepublic · Published 2026-10-15 · First collected 2026-10-24

• Descope’s Agentic Identity Hub 3.0 takes aim at shadow AI agents inside companies ↗ (opens in a new tab)

  Security - SiliconANGLE · Published 2026-10-15 · First collected 2026-10-24

• Insignary Launches Clarity AIR to Detect Undeclared Open-Source and AI-Written Code ↗ (opens in a new tab)

  HackerNoon - cybersecurity · Published 2026-10-08 · First collected 2026-10-24

• How to Secure AI in Stadium Operations ↗ (opens in a new tab)

  Cloud Security Alliance · Published 2026-09-30 · First collected 2026-10-24

• How to achieve first-pass quality with AI coding agents ↗ (opens in a new tab)

  Sonar Blog · Published 2026-09-29 · First collected 2026-10-24

• The Infostealer Incursion: How Stolen Credentials Breach Cloud, Code, and AI Environments ↗ (opens in a new tab)

  Wiz Blog | RSS feed · Published 2026-09-25 · First collected 2026-10-24

• What is an agent harness (and how do you secure one)? ↗ (opens in a new tab)

  Adversa AI — Trusted AI Blog · Published 2026-09-14 · First collected 2026-10-24

• vRon Lets the Dogs Out ↗ (opens in a new tab)

  Berryville Institute of Machine Learning · Published 2026-09-03 · First collected 2026-10-24

• Claude Code Security: Pros, cons — and best practices ↗ (opens in a new tab)

  ReversingLabs Blog · Published 2026-08-27 · First collected 2026-10-24

• Why Your AI Application Is Exposed (Even When Your Scans Come Back Clean) ↗ (opens in a new tab)

  Blog RSS Feed | Snyk · Published 2026-08-26 · First collected 2026-10-24

• Verified loops: Building AI agent trust and accountability ↗ (opens in a new tab)

  Blog on 1Password Blog · Published 2026-08-11 · First collected 2026-10-24

• Vulnerability response in the AI-discovery era: A four-part plan ↗ (opens in a new tab)

  Sysdig Blog · Published 2026-08-11 · First collected 2026-10-24

• Meta Confirms One of Its AI Models Breached a Company During a Misconfigured Cyber Test ↗ (opens in a new tab)

  Cybersecurity News: Threats, Vulnerabilities & Privacy Updates - gHacks · Published 2026-08-10 · First collected 2026-10-24

• [tl;dr sec] #340 - Anthropic and Meta Agents be Hackin', Agentic Incident Response Notebooks, Figma's AI Code Scanning ↗ (opens in a new tab)

  tl;dr sec · Published 2026-08-07 · First collected 2026-10-24

• Navigating AI Tokenomics: from cost uncertainty to operational scale ↗ (opens in a new tab)

  Cisco Newsroom: Security · Published 2026-07-29 · First collected 2026-10-24

• The Hugging Face Incident Proved the Real AI Risk Is in the Action Layer ↗ (opens in a new tab)

  Salt Security Blog · Published 2026-07-24 · First collected 2026-10-24

• The AI Exchange: Innovators in Payment Security Featuring PROSA ↗ (opens in a new tab)

  PCI Perspectives · Published 2026-07-10 · First collected 2026-10-24

• What happened after 2,000 people tried to hack my AI assistant ↗ (opens in a new tab)

  Simon Willison: prompt injection · Published 2026-06-26 · First collected 2026-10-24

• Computer-Use and TOCTOU: What You Click Is Not What You Get! ↗ (opens in a new tab)

  Embrace The Red · Published 2026-06-25 · First collected 2026-10-24

• AI Penetration Testing vs Traditional Penetration Testing: Changes in 2026 ↗ (opens in a new tab)

  OffSec RSS Feed · Published 2026-06-09 · First collected 2026-10-24

• Agentic Governance: Why It Matters Now ↗ (opens in a new tab)

  Trend Micro Research, News and Perspectives · Published 2026-05-18 · First collected 2026-10-24

• GPT-5.2 Initial Trust and Safety Assessment ↗ (opens in a new tab)

  Promptfoo Blog · Published 2025-12-11 · First collected 2026-10-24

• Top hyperscalers likely to have more AI-linked debt than now known ↗ (opens in a new tab)

  iTnews · Published 2026-10-19 · First collected 2026-10-24

• Proofpoint gives MSPs a Microsoft 365 risk dashboard, Teams training and an AI assistant ↗ (opens in a new tab)

  Security - SiliconANGLE · Published 2026-10-15 · First collected 2026-10-24

• We Learned How to Moderate Social Media: AI Is a Much Harder Problem ↗ (opens in a new tab)

  HackerNoon - cybersecurity · Published 2026-10-07 · First collected 2026-10-24