Mithril Security's blog covers confidential computing, trusted execution environments and AI security, including tools for verifiable AI training and tests and analyses of hardware security claims. Readers get technical write-ups on protecting AI models from tampering, cheating and supply chain attacks.
Website: https://blog.mithrilsecurity.io/
A technical newsletter on building, securing, and operating autonomous AI agents, covering retrieval architecture like GraphRAG, reward hacking risks, and LLM inference optimization. Readers get architecture patterns, security perspectives, and engineering guidance for shipping agentic systems.
Covers cybersecurity news, breaches and cybercrime, with OSINT-backed investigations and short analysis of what is and is not known. Includes a Friday roundup of the week's incidents and standalone breach reports, such as Meta's GitHub intrusion and Revolut's disclosure to a fake government request.
A company blog covering security for AI agents, including prompt injection, session behavior analysis and runtime policy enforcement for coding agents. Readers get product announcements alongside technical explanations of how the features are built and the threat models behind them.
A curated library of AI governance resources, with weekly issues that open with an essay and then summarise reports, frameworks and standards. Readers get orientation on AI governance, security and risk material, including OWASP guidance and industry survey reports.
One short email a week with hand-picked newsletters from the index. Free, no spam, unsubscribe anytime.
