Experimental News Clipping Site

Tag: detection evasion

  • The Register: MINJA sneak attack poisons AI models for other chatbot users

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/03/11/minja_attack_poisons_ai_model_memory/ Source: The Register Title: MINJA sneak attack poisons AI models for other chatbot users Feedly Summary: Nothing like an OpenAI-powered agent leaking data or getting confused over what someone else whispered to it AI models with memory aim to enhance user interactions by recalling past engagements. However, this feature opens the door…

  • Cloud Blog: Adversarial Misuse of Generative AI

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloud.google.com/blog/topics/threat-intelligence/adversarial-misuse-generative-ai/ Source: Cloud Blog Title: Adversarial Misuse of Generative AI Feedly Summary: Rapid advancements in artificial intelligence (AI) are unlocking new possibilities for the way we work and accelerating innovation in science, technology, and beyond. In cybersecurity, AI is poised to transform digital defense, empowering defenders and enhancing our collective security. Large language…

  • Hacker News: Windows Process Injection

    —

    by

    system automation
    in

    Source URL: https://www.outflank.nl/blog/2024/10/15/introducing-early-cascade-injection-from-windows-process-creation-to-stealthy-injection/ Source: Hacker News Title: Windows Process Injection Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The text introduces a novel process injection technique dubbed Early Cascade Injection, which enhances existing methods by executing more stealthily against Endpoint Detection and Response (EDR) systems. The author provides a detailed technical analysis of Windows…