RMF – Experimental News Clipping Site

Docker: From Hallucinations to Prompt Injection: Securing AI Workflows at Runtime

Sep 10, 2025

—

by

Source URL: https://www.docker.com/blog/secure-ai-agents-runtime-security/ Source: Docker Title: From Hallucinations to Prompt Injection: Securing AI Workflows at Runtime Feedly Summary: How developers are embedding runtime security to safely build with AI agents Introduction: When AI Workflows Become Attack Surfaces The AI tools we use today are powerful, but also unpredictable and exploitable. You prompt an LLM and…

Schneier on Security: Indirect Prompt Injection Attacks Against LLM Assistants

Sep 3, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://www.schneier.com/blog/archives/2025/09/indirect-prompt-injection-attacks-against-llm-assistants.html Source: Schneier on Security Title: Indirect Prompt Injection Attacks Against LLM Assistants Feedly Summary: Really good research on practical attacks against LLM agents. “Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous” Abstract: The growing integration of LLMs into applications has introduced new security risks,…

Unit 42: Model Namespace Reuse: An AI Supply-Chain Attack Exploiting Model Name Trust

Sep 3, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://unit42.paloaltonetworks.com/model-namespace-reuse/ Source: Unit 42 Title: Model Namespace Reuse: An AI Supply-Chain Attack Exploiting Model Name Trust Feedly Summary: Model namespace reuse is a potential security risk in the AI supply chain. Attackers can misuse platforms like Hugging Face for remote code execution. The post Model Namespace Reuse: An AI Supply-Chain Attack Exploiting Model…

The Register: Internet mapping and research tool Censys reveals state-based abuse, harassment

Sep 3, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://www.theregister.com/2025/09/03/censys_abuse_sigcomm_paper/ Source: The Register Title: Internet mapping and research tool Censys reveals state-based abuse, harassment Feedly Summary: ‘Universities are being used to proxy offensive government operations, turning research access decisions political’ Censys Inc, vendor of the popular Censys internet-mapping tool, has revealed that state-based actors are trying to abuse its services by hiding…

Bulletins: Vulnerability Summary for the Week of August 25, 2025

Sep 2, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://www.cisa.gov/news-events/bulletins/sb25-245 Source: Bulletins Title: Vulnerability Summary for the Week of August 25, 2025 Feedly Summary: High Vulnerabilities PrimaryVendor — Product Description Published CVSS Score Source Info 1000projects–Online Project Report Submission and Evaluation System A vulnerability has been found in 1000projects Online Project Report Submission and Evaluation System 1.0. This issue affects some unknown…

NCSC Feed: From bugs to bypasses: adapting vulnerability disclosure for AI safeguards

Sep 2, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://www.ncsc.gov.uk/blog-post/from-bugs-to-bypasses-adapting-vulnerability-disclosure-for-ai-safeguards Source: NCSC Feed Title: From bugs to bypasses: adapting vulnerability disclosure for AI safeguards Feedly Summary: Exploring how far cyber security approaches can help mitigate risks in generative AI systems AI Summary and Description: Yes Summary: The text addresses the intersection of cybersecurity strategies and generative AI systems, highlighting how established cybersecurity…

Slashdot: Meta Changes Teen AI Chatbot Responses as Senate Begins Probe Into ‘Romantic’ Conversations

Aug 30, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://tech.slashdot.org/story/25/08/29/2116246/meta-changes-teen-ai-chatbot-responses-as-senate-begins-probe-into-romantic-conversations Source: Slashdot Title: Meta Changes Teen AI Chatbot Responses as Senate Begins Probe Into ‘Romantic’ Conversations Feedly Summary: AI Summary and Description: Yes Summary: Meta is instituting temporary limitations on its AI chatbots for teenage users to safeguard them from engaging in inappropriate conversations. The adjustments aim to redirect conversations away from…

The Register: Researcher who found McDonald’s free-food hack turns her attention to Chinese restaurant robots

Aug 29, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://www.theregister.com/2025/08/29/pudu_robots_hackable/ Source: The Register Title: Researcher who found McDonald’s free-food hack turns her attention to Chinese restaurant robots Feedly Summary: The admin controls were left wide open on Pudu’s robots A researcher caught the world’s leading supplier of commercial service robots using shoddy admin security that let attackers redirect the delivery machines to…

Cloud Blog: Run Gemini anywhere, including on-premises, with Google Distributed Cloud

Aug 28, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://cloud.google.com/blog/topics/hybrid-cloud/gemini-is-now-available-anywhere/ Source: Cloud Blog Title: Run Gemini anywhere, including on-premises, with Google Distributed Cloud Feedly Summary: Earlier this year, we announced our commitment to bring Gemini to on-premises environments with Google Distributed Cloud (GDC). Today, we are excited to announce that Gemini on GDC is now available to customers. For years, enterprises and…

Slashdot: One Long Sentence is All It Takes To Make LLMs Misbehave

Aug 27, 2025

—

by

Kurt Seifried

in Uncategorized

Source URL: https://slashdot.org/story/25/08/27/1756253/one-long-sentence-is-all-it-takes-to-make-llms-misbehave?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: One Long Sentence is All It Takes To Make LLMs Misbehave Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a significant security research finding from Palo Alto Networks’ Unit 42 regarding vulnerabilities in large language models (LLMs). The researchers explored methods that allow users to bypass…

Tag: RMF