❌

Reading view

The WHO’s High-Price Pandemic Plan Is Built on Smoke and Mirrors

The WHO and the World Bank want $31 billion a year for pandemic preparedness – but a new Leeds University study says the financial case is built on dubious assumptions and false accounting.

The post The WHO’s High-Price Pandemic Plan Is Built on Smoke and Mirrors appeared first on The Daily Sceptic.

  •  

Grok exfiltrates user data when malicious instructions are encrypted

Earlier this week, researchers outlined an attack that used a secret input provided by Microsoft 365 Copilot for enterprise to cause the AI assistant to exfiltrate a password present in the user’s inbox. Now, a separate team has devised a similar attack against Grok. The new data theft hack employs a deceptively simple trick to force the Elon Musk-owned large language model to steal user chats and other personal information. At the time this post went live, the assistant continued to cough up the data, despite xAI being informed of it in June.

The lesson from both this week’s episodesβ€”and the countless other ones that have come before itβ€”is that LLMs are incapable of solving the root causes for prompt injections, the most severe vulnerability classes they’re most prone to. That leaves AI developers with no other option but to build a guardrail that steers the model away from the harmful actions. As I noted in Tuesday’s story, the approach is tantamount to a road traffic safety engineer erecting a protective rail around a dangerous bend rather than banking the curve.

Cryptographic Context Injection in the house

Prompt injections exploit LLMs' training to comply with user requests whenever possible. Attackers can capitalize on the predilection by smuggling harmful instructions into emails or webpages the assistant is instructed to summarize. Because LLMs can’t reliably distinguish between content in an email sent by an untrusted party and user instructions entered directly into a prompt, the overly solicitous LLM faithfully follows them. To date, Grok and other LLMs' only recourse is to create guardrails that flag suspicious instructions and forbid them from being executed.

Read full article

Comments

Β© Getty Images | SOPA Images

  •  

β€˜LION’ – new TV series chronicles four-year journey of lion cub Kio

It’s very much a real-life doco version of β€˜The Lion King’, with Jon Favreau executive producing, and music from Hans Zimmer echoing themes from the Disney classic. It took Disney+ and BBC Studios’...

The post β€˜LION’ – new TV series chronicles four-year journey of lion cub Kio first appeared on Science Illustrated.

  •  
❌