Tag: RMF

Source URL: https://www.schneier.com/blog/archives/2025/08/subverting-aiops-systems-through-poisoned-input-data.html Source: Schneier on Security Title: Subverting AIOps Systems Through Poisoned Input Data Feedly Summary: In this input integrity attack against an AI system, researchers were able to fool AIOps tools: AIOps refers to the use of LLM-based agents to gather and analyze application telemetry, including system logs, performance metrics, traces, and alerts,…

Simon Willison’s Weblog: The Summer of Johann: prompt injections as far as the eye can see

—

by

Source URL: https://simonwillison.net/2025/Aug/15/the-summer-of-johann/#atom-everything Source: Simon Willison’s Weblog Title: The Summer of Johann: prompt injections as far as the eye can see Feedly Summary: Independent AI researcher Johann Rehberger has had an absurdly busy August. Under the heading The Month of AI Bugs he has been publishing one report per day across an array of different…

Simon Willison’s Weblog: Meta’s AI rules have let bots hold ‘sensual’ chats with kids, offer false medical info

—

by

Source URL: https://simonwillison.net/2025/Aug/15/metas-ai-rules/ Source: Simon Willison’s Weblog Title: Meta’s AI rules have let bots hold ‘sensual’ chats with kids, offer false medical info Feedly Summary: Meta’s AI rules have let bots hold ‘sensual’ chats with kids, offer false medical info This is grim. Reuters got hold of a leaked copy Meta’s internal “GenAI: Content Risk…

Cloud Blog: Beyond guardrails: A taxonomy of platform engineering control mechanisms

—

by

Source URL: https://cloud.google.com/blog/products/application-modernization/platform-engineering-control-mechanisms/ Source: Cloud Blog Title: Beyond guardrails: A taxonomy of platform engineering control mechanisms Feedly Summary: The promise of platform engineering is to accelerate software delivery by empowering developers with self-service capabilities. However, this must be balanced with security, compliance, and operational stability, and for this, you need robust controls. But all too…

The Register: LLM chatbots trivial to weaponise for data theft, say boffins

—

by

Source URL: https://www.theregister.com/2025/08/15/llm_chatbots_trivial_to_weaponise/ Source: The Register Title: LLM chatbots trivial to weaponise for data theft, say boffins Feedly Summary: System prompt engineering turns benign AI assistants into ‘investigator’ and ‘detective’ roles that bypass privacy guardrails A team of boffins is warning that AI chatbots built on large language models (LLM) can be tuned into malicious…

Slashdot: Meta’s AI Rules Have Let Bots Hold ‘Sensual’ Chats With Kids, Offer False Medical Info

Aug 14, 2025

—

by

Source URL: https://tech.slashdot.org/story/25/08/14/1759222/metas-ai-rules-have-let-bots-hold-sensual-chats-with-kids-offer-false-medical-info?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Meta’s AI Rules Have Let Bots Hold ‘Sensual’ Chats With Kids, Offer False Medical Info Feedly Summary: AI Summary and Description: Yes Summary: The document raises significant concerns regarding the ethical implications of AI use in children’s interactions and the propagation of harmful stereotypes. This situation emphasizes the importance…

Embrace The Red: Jules Zombie Agent: From Prompt Injection to Remote Control

Aug 14, 2025

—

by

Source URL: https://embracethered.com/blog/posts/2025/google-jules-remote-code-execution-zombai/ Source: Embrace The Red Title: Jules Zombie Agent: From Prompt Injection to Remote Control Feedly Summary: In the previous post, we explored two data exfiltration vectors that Jules is vulnerable to and that can be exploited via prompt injection. This post takes it further by demonstrating how Jules can be convinced to…

Wired: OpenAI Designed GPT-5 to Be Safer. It Still Outputs Gay Slurs

Aug 13, 2025

—

by

Source URL: https://www.wired.com/story/openai-gpt5-safety/ Source: Wired Title: OpenAI Designed GPT-5 to Be Safer. It Still Outputs Gay Slurs Feedly Summary: The new version of ChatGPT explains why it won’t generate rule-breaking outputs. WIRED’s initial analysis found that some guardrails were easy to circumvent. AI Summary and Description: Yes Summary: The text discusses a new version of…

Slashdot: Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ For Enterprise

Aug 9, 2025

—

by