Experimental News Clipping Site

Tag: prompt injections

  • Microsoft Security Blog: Securing DeepSeek and other AI systems with Microsoft Security

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.microsoft.com/en-us/security/blog/2025/02/13/securing-deepseek-and-other-ai-systems-with-microsoft-security/ Source: Microsoft Security Blog Title: Securing DeepSeek and other AI systems with Microsoft Security Feedly Summary: Microsoft Security provides cyberthreat protection, posture management, data security, compliance and governance, and AI safety, to secure AI applications that you build and use. These capabilities can also be used to secure and govern AI apps…

  • Simon Willison’s Weblog: How we estimate the risk from prompt injection attacks on AI systems

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jan/29/prompt-injection-attacks-on-ai-systems/ Source: Simon Willison’s Weblog Title: How we estimate the risk from prompt injection attacks on AI systems Feedly Summary: How we estimate the risk from prompt injection attacks on AI systems The “Agentic AI Security Team" at Google DeepMind share some details on how they are researching indirect prompt injection attacks. They…

  • 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…

  • Google Online Security Blog: How we estimate the risk from prompt injection attacks on AI systems

    —

    by

    Kurt Seifried
    in

    Source URL: https://security.googleblog.com/2025/01/how-we-estimate-risk-from-prompt.html Source: Google Online Security Blog Title: How we estimate the risk from prompt injection attacks on AI systems Feedly Summary: AI Summary and Description: Yes Summary: The text discusses emerging security challenges in modern AI systems, specifically focusing on a class of attacks called “indirect prompt injection.” It presents a comprehensive evaluation…

  • Simon Willison’s Weblog: Introducing Operator

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jan/23/introducing-operator/ Source: Simon Willison’s Weblog Title: Introducing Operator Feedly Summary: Introducing Operator OpenAI released their “research preview" today of Operator, a cloud-based browser automation platform rolling out today to $200/month ChatGPT Pro subscribers. They’re calling this their first "agent". In the Operator announcement video Sam Altman defined that notoriously vague term like this:…

  • The Register: Microsoft dangles $10K for hackers to hijack LLM email service

    —

    by

    system automation
    in

    Source URL: https://www.theregister.com/2024/12/09/microsoft_llm_prompt_injection_challenge/ Source: The Register Title: Microsoft dangles $10K for hackers to hijack LLM email service Feedly Summary: Outsmart an AI, win a little Christmas cash Microsoft and friends have challenged AI hackers to break a simulated LLM-integrated email client with a prompt injection attack – and the winning teams will share a $10,000…

  • Embrace The Red: Terminal DiLLMa: LLM-powered Apps Can Hijack Your Terminal Via Prompt Injection

    —

    by

    system automation
    in

    Source URL: https://embracethered.com/blog/posts/2024/terminal-dillmas-prompt-injection-ansi-sequences/ Source: Embrace The Red Title: Terminal DiLLMa: LLM-powered Apps Can Hijack Your Terminal Via Prompt Injection Feedly Summary: Last week Leon Derczynski described how LLMs can output ANSI escape codes. These codes, also known as control characters, are interpreted by terminal emulators and modify behavior. This discovery resonates with areas I had…

  • Simon Willison’s Weblog: 0xfreysa/agent

    —

    by

    system automation
    in

    Source URL: https://simonwillison.net/2024/Nov/29/0xfreysaagent/#atom-everything Source: Simon Willison’s Weblog Title: 0xfreysa/agent Feedly Summary: 0xfreysa/agent Freysa describes itself as “the world’s first adversarial agent game". On 22nd November they released an LLM-driven application which people could pay to message (using Ethereum), with access to tools that could transfer a prize pool to the message sender, ending the game.…

  • Hacker News: The Beginner’s Guide to Visual Prompt Injections

    —

    by

    system automation
    in

    Source URL: https://www.lakera.ai/blog/visual-prompt-injections Source: Hacker News Title: The Beginner’s Guide to Visual Prompt Injections Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses security vulnerabilities inherent in Large Language Models (LLMs), particularly focusing on visual prompt injections. As the reliance on models like GPT-4 increases for various tasks, concerns regarding the potential…

  • Schneier on Security: Prompt Injection Defenses Against LLM Cyberattacks

    —

    by

    system automation
    in

    Source URL: https://www.schneier.com/blog/archives/2024/11/prompt-injection-defenses-against-llm-cyberattacks.html Source: Schneier on Security Title: Prompt Injection Defenses Against LLM Cyberattacks Feedly Summary: Interesting research: “Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks“: Large language models (LLMs) are increasingly being harnessed to automate cyberattacks, making sophisticated exploits more accessible and scalable. In response, we propose a new defense…