Security briefing · Archive
AI & security · Archive
Browse collected headlines by topic and follow links to the original publishers.
AI & security
Dates are publishers’ publication dates, source update dates, or CISA catalog-added dates. First collected records when SecSIG first saw the entry.
PHP2Shell and what the AI headlines are missing ↗ (opens in a new tab)
Job Seekers Who Use AI for Applications Need to be on the Lookout for Scams ↗ (opens in a new tab)
Cellebrite Genesis vs. ChatGPT: Why You Need Purpose-Built Investigative AI ↗ (opens in a new tab)
Agentic AI helps hackers level up, even without detailed instructions ↗ (opens in a new tab)
Managing AI token consumption for operational resilience - ITSM.00.125 ↗ (opens in a new tab)
Securing the Software Development Lifecycle and Supply Chain in an AI-Forward World ↗ (opens in a new tab)
The True Blast Radius of an AI Attack ↗ (opens in a new tab)
How do you verify AI coding agent output from any tool, not just one? ↗ (opens in a new tab)
Keeper Security Launches AI-Powered Phishing Protection to Block Credential Theft ↗ (opens in a new tab)
Can LLMs Supercharge Geolocations? Our Tests Show Big Improvements But Humans Remain Key ↗ (opens in a new tab)
Microsoft: Chinese State Actor Used AI to Compromise ConnectWise Tenants ↗ (opens in a new tab)
The Keys Are in the Browser: Secret Exposure Across AI-Built Websites ↗ (opens in a new tab)
New LiteLLM Supply Chain Attack Hits PyPI and Docker ↗ (opens in a new tab)
Is Claude Code safe for the enterprise? What the official settings cover, and what they don't ↗ (opens in a new tab)
Turn Your Vulnerability Backlog Into Pull Requests With Agentic Remediation ↗ (opens in a new tab)
Exploring the Risks and Impacts of AI on Vulnerability Discovery and Exploitation ↗ (opens in a new tab)
Unprompted: When AI Agents Expose Data Without an Attacker ↗ (opens in a new tab)
Inside a Global AI-Assisted Hacking Campaign ↗ (opens in a new tab)
WhatsApp’s chatbot was given hidden instructions to not mention privacy regulators ↗ (opens in a new tab)
The Domain Drop Race: How an AI-Powered Squatting Pipeline Hunts Expiring Names | UpGuard ↗ (opens in a new tab)
[Security Blog] HKCERT Warns of Critical “PHP2Shell” Vulnerabilities: Businesses Must Immediately Review and Patch PHP Systems AI Accelerates Cyber Attacks and Defence, Further Shortening the Response Window Between Vulnerability Disclosure and Exploitation ↗ (opens in a new tab)
Your AI agent fixed the bug, but what else did it change? ↗ (opens in a new tab)
“Next Exploit Opportunities”: How a Threat Actor Used AI to Help Plan and Execute Multiple Types of Cybercrime Activities ↗ (opens in a new tab)
Benchmark Your AI Security Maturity in Under a Minute ↗ (opens in a new tab)
AI Webinar Series Replay ↗ (opens in a new tab)
GAO outlines 2027-2032 agenda for congressional oversight of federal cyber defenses, critical infrastructure, AI risks ↗ (opens in a new tab)
Advancing Agentic AI Security with Palo Alto Networks and NVIDIA ↗ (opens in a new tab)
Autonomous LLMjacking: ‘Skynet’ Agent Hijacks Exposed AI Models to Run Attacks ↗ (opens in a new tab)
How Some Malicious AI Skills Hide Instructions from Reviewers ↗ (opens in a new tab)
Shadow AI Detection Now Extends to Developer Workstations ↗ (opens in a new tab)