FeedBagel

All Topics

Art

A Three-Minute Protocol to Reduce AI Manipulation Risk

Yuksel Aydin. <p>Yuksel Aydin is chief information security officer at RSM France and an AI security researcher.</p>

1mo agoen

cybersecurity artificial intelligence business data security

Source

MITA Three-Minute Protocol to Reduce AI Manipulation Riskmit.edu

Snippet from the RSS feed

izusek/Getty Images Of the potential weaknesses of any security system, the human layer has always posed a key risk. The arrival of AI tools has made human cognition even more of a vulnerability. Companies face three overlapping security threats from AI’s effects on human cognition. First, weaponized persuasion lets attackers manipulate employees’ judgment through personalized, […]

You might also wanna read

Research Warns AI Chatbot Reliance May Impair Human Cognitive Abilities

The article discusses research findings that over-reliance on AI chatbots and large language models for cognitive tasks may negatively impac

bbc.com·2mo ago

Study Shows AI Chatbots Vulnerable to Psychological Manipulation Tactics

Researchers from the University of Pennsylvania successfully manipulated OpenAI's GPT-4o Mini chatbot into breaking its own safety rules usi

The Verge·10mo ago

How AI and Human Expertise Combine for Stronger Cybersecurity Defense

This article explores the intersection of traditional cybersecurity practices ("hard work") and AI-driven automation ("smart work") in build

undercodetesting.com·10d ago

Study finds warning labels shift perceptions of sycophantic AI but fail to reduce its influence on users

A preregistered experiment with 2,610 participants tested whether warning labels mitigate the influence of sycophantic AI on user judgment.

arxiv.org·13d ago

Study finds warning labels shift perceptions of sycophantic AI but fail to reduce its influence on users

A preregistered experiment with 2,610 participants tested whether warning labels mitigate the influence of sycophantic AI on user judgment.

arxiv.org·13d ago

Researchers Warn of Poor Security Practices in AI Development

The article discusses the alarming lack of robust security practices in the development and deployment of artificial intelligence (AI), as h

scworld.com·10mo ago

AI tools produce fewer hallucinations but more confidently wrong answers, study warns

AI tools are producing fewer obvious hallucinations but are increasingly generating inaccurate information presented with polished, hyper-co

axios.com·1mo ago

AI tools produce fewer hallucinations but more confidently wrong answers, study warns

AI tools are producing fewer obvious hallucinations but are increasingly generating inaccurate information presented with polished, hyper-co

axios.com·1mo ago

Comments

No comments yet. Be the first.