Experimental News Clipping Site

Tag: exfiltration

  • 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…

  • Hacker News: Microsoft Probing If DeepSeek-Linked Group Improperly Obtained OpenAI Data

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.bloomberg.com/news/articles/2025-01-29/microsoft-probing-if-deepseek-linked-group-improperly-obtained-openai-data Source: Hacker News Title: Microsoft Probing If DeepSeek-Linked Group Improperly Obtained OpenAI Data Feedly Summary: Comments AI Summary and Description: Yes Summary: Microsoft and OpenAI are reportedly investigating a potential data exfiltration incident involving their technology linked to a Chinese AI startup, DeepSeek. This raises critical concerns about security and integrity in…

  • Hacker News: Hacker infects 18,000 "script kiddies" with fake malware builder

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.bleepingcomputer.com/news/security/hacker-infects-18-000-script-kiddies-with-fake-malware-builder/ Source: Hacker News Title: Hacker infects 18,000 "script kiddies" with fake malware builder Feedly Summary: Comments AI Summary and Description: Yes Summary: A recent report by CloudSEK reveals how a Trojanized version of the XWorm RAT builder was weaponized and distributed, unknowingly compromising low-skilled hackers, or “script kiddies”. This incident underscores the…

  • Simon Willison’s Weblog: Lessons From Red Teaming 100 Generative AI Products

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jan/18/lessons-from-red-teaming/ Source: Simon Willison’s Weblog Title: Lessons From Red Teaming 100 Generative AI Products Feedly Summary: Lessons From Red Teaming 100 Generative AI Products New paper from Microsoft describing their top eight lessons learned red teaming (deliberately seeking security vulnerabilities in) 100 different generative AI models and products over the past few years.…

  • CSA: Unpacking the LastPass Hack: A Case Study

    —

    by

    Kurt Seifried
    in

    Source URL: https://insidersecurity.co/lastpass-hack-illustrative-case-study/ Source: CSA Title: Unpacking the LastPass Hack: A Case Study Feedly Summary: AI Summary and Description: Yes Summary: The text provides an in-depth analysis of the LastPass hack, emphasizing the importance of security practices in cloud computing and software services. It discusses the vulnerabilities exploited during the breach, the implications of the…

  • Slashdot: Snyk Researcher Caught Deploying Malicious Code Targeting AI Startup

    —

    by

    Kurt Seifried
    in

    Source URL: https://it.slashdot.org/story/25/01/14/0920245/snyk-researcher-caught-deploying-malicious-code-targeting-ai-startup Source: Slashdot Title: Snyk Researcher Caught Deploying Malicious Code Targeting AI Startup Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a dependency confusion attack targeting Cursor, an AI coding startup, via the publication of malicious NPM packages. This incident raises significant concerns regarding supply chain security and illustrates potential…

  • The Register: Cryptojacking, backdoors abound as attackers abuse Aviatrix Controller bug

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.theregister.com/2025/01/13/severe_aviatrix_controller_vulnerability/ Source: The Register Title: Cryptojacking, backdoors abound as attackers abuse Aviatrix Controller bug Feedly Summary: This is what happens when you publish PoCs immediately “Several cloud deployments" are already compromised following the disclosure of the maximum-severity vulnerability in Aviatrix Controller, researchers say.… AI Summary and Description: Yes Summary: The text discusses a…