injection - Cloud Security Alliance News Clipping Site

Simon Willison’s Weblog: Quoting Question for Department for Science, Innovation and Technology

Nov 1, 2024

—

by

Source URL: https://simonwillison.net/2024/Nov/1/prompt-injection/#atom-everything Source: Simon Willison’s Weblog Title: Quoting Question for Department for Science, Innovation and Technology Feedly Summary: Lord Clement-Jones: To ask His Majesty’s Government what assessment they have made of the cybersecurity risks posed by prompt injection attacks to the processing by generative artificial intelligence of material provided from outside government, and whether…

The Register: Google reportedly developing an AI agent that can control your browser

Oct 28, 2024

—

by

system automation

in Uncategorized

Source URL: https://www.theregister.com/2024/10/28/google_ai_web_agent/ Source: The Register Title: Google reportedly developing an AI agent that can control your browser Feedly Summary: Project Jarvis will apparently conduct research, purchase products, and even book a flight on your behalf Google is reportedly looking to sidestep the complexity of AI-driven automation by letting its multimodal large language models (LLMs)…

Slashdot: Researchers Discover Flaws In 5 End-to-End Encrypted Cloud Services

Oct 26, 2024

—

by

system automation

in Uncategorized

Source URL: https://it.slashdot.org/story/24/10/26/1833203/researchers-discover-flaws-in-5-end-to-end-encrypted-cloud-services?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Researchers Discover Flaws In 5 End-to-End Encrypted Cloud Services Feedly Summary: AI Summary and Description: Yes Summary: Researchers from ETH Zurich have uncovered significant cryptographic flaws in several major end-to-end encrypted cloud storage services, compromising their intended confidentiality and security. The findings highlight the vulnerabilities in commonly used services…

Simon Willison’s Weblog: ZombAIs: From Prompt Injection to C2 with Claude Computer Use

Oct 25, 2024

—

by

system automation

in Uncategorized

Source URL: https://simonwillison.net/2024/Oct/25/zombais/ Source: Simon Willison’s Weblog Title: ZombAIs: From Prompt Injection to C2 with Claude Computer Use Feedly Summary: ZombAIs: From Prompt Injection to C2 with Claude Computer Use In news that should surprise nobody who has been paying attention, Johann Rehberger has demonstrated a prompt injection attack against the new Claude Computer Use…

Embrace The Red: ZombAIs: From Prompt Injection to C2 with Claude Computer Use

Oct 25, 2024

—

by

system automation

in Uncategorized

Source URL: https://embracethered.com/blog/posts/2024/claude-computer-use-c2-the-zombais-are-coming/ Source: Embrace The Red Title: ZombAIs: From Prompt Injection to C2 with Claude Computer Use Feedly Summary: A few days ago, Anthropic released Claude Computer Use, which is a model + code that allows Claude to control a computer. It takes screenshots to make decisions, can run bash commands and so forth.…

The Register: Anthropic’s latest Claude model can interact with computers – what could go wrong?

Oct 24, 2024

—

by

system automation

in Uncategorized

Source URL: https://www.theregister.com/2024/10/24/anthropic_claude_model_can_use_computers/ Source: The Register Title: Anthropic’s latest Claude model can interact with computers – what could go wrong? Feedly Summary: For starters, it could launch a prompt injection attack on itself… The latest version of AI startup Anthropic’s Claude 3.5 Sonnet model can use computers – and the developer makes it sound like…

The Register: Microsoft SharePoint RCE flaw exploits in the wild – you’ve had 3 months to patch

Oct 23, 2024

—

by

system automation

in Uncategorized

Source URL: https://www.theregister.com/2024/10/23/microsoft_sharepoint_rce_exploited/ Source: The Register Title: Microsoft SharePoint RCE flaw exploits in the wild – you’ve had 3 months to patch Feedly Summary: Plus, a POC to make it extra easy for attackers A Microsoft SharePoint bug that can allow an attacker to remotely inject code into vulnerable versions is under active exploitation, according…

Simon Willison’s Weblog: Quoting Model Card Addendum: Claude 3.5 Haiku and Upgraded Sonnet

Oct 23, 2024

—

by

system automation

in Uncategorized

Source URL: https://simonwillison.net/2024/Oct/23/model-card/#atom-everything Source: Simon Willison’s Weblog Title: Quoting Model Card Addendum: Claude 3.5 Haiku and Upgraded Sonnet Feedly Summary: We enhanced the ability of the upgraded Claude 3.5 Sonnet and Claude 3.5 Haiku to recognize and resist prompt injection attempts. Prompt injection is an attack where a malicious user feeds instructions to a model…

METR Blog – METR: An update on our general capability evaluations

Oct 23, 2024

—

by

system automation

in Uncategorized

Source URL: https://metr.org/blog/2024-08-06-update-on-evaluations/ Source: METR Blog – METR Title: An update on our general capability evaluations Feedly Summary: AI Summary and Description: Yes **Summary:** The provided text discusses the development of evaluation metrics for AI capabilities, particularly focusing on autonomous systems. It aims to create measures that can assess general autonomy rather than solely relying…

Simon Willison’s Weblog: Initial explorations of Anthropic’s new Computer Use capability

Oct 22, 2024

—

by

system automation

in Uncategorized

Source URL: https://simonwillison.net/2024/Oct/22/computer-use/#atom-everything Source: Simon Willison’s Weblog Title: Initial explorations of Anthropic’s new Computer Use capability Feedly Summary: Two big announcements from Anthropic today: a new Claude 3.5 Sonnet model and a new API mode that they are calling computer use. (They also pre-announced Haiku 3.5, but that’s not available yet so I’m ignoring it…

Tag: injection