FIU study reveals image-based vulnerability in AI chatbots as lawsuits mount against tech companies
By
Laurie Mermet
Summary
Florida International University researchers have discovered a vulnerability in AI chatbots where tiny, nearly invisible modifications to images can trick the systems into bypassing their own safety restrictions and responding to harmful prompts. The research comes amid growing legal pressure on AI companies, including a lawsuit filed by a Jupiter, Florida family in March, alleging that chatbots have led users into dangerous situations. The study aims to identify weaknesses in AI systems to help build more robust safeguards.
Source
bskyFIU study reveals image-based vulnerability in AI chatbots as lawsuits mount against tech companiessun-sentinel.comKey quotes
· 3 pulledSmall, almost invisible tweaks to an image were enough to push certain AI chatbots into responding to requests they're designed to block, their study shows.
The finding comes as multiple lawsuits, including one filed by a Jupiter family in March, accuse AI companies of failing to prevent their chatbots from leading the people who use them into harmful situations.
The study, whose goal is to identify weaknesses in AI systems to help build stronger defenses.
You might also wanna read
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
Research Shows Poetry Can Circumvent AI Chatbot Safety Features
New research from Italy's Icaro Lab reveals that AI chatbots can be manipulated into producing harmful content like child sex abuse material
The Verge·7mo ago
Privacy Risks of AI Chatbots with Memory Features
This article explores the significant privacy risks associated with AI chatbots like ChatGPT that have memory capabilities. It presents hypo
futureofbeinghuman.com·9mo ago
Study Finds AI Chatbots Vulnerable to Jailbreak Attacks Using Poetic Prompts
Researchers discovered that AI chatbots like ChatGPT can be tricked into providing dangerous information about nuclear weapons, child sex ab
wired.com·7mo ago
Study Reveals Risks of AI Chatbots in Mental Health Support
A study reveals the concerning blind spots of AI chatbots like ChatGPT in responding to individuals with mental health issues, highlighting
the-independent.com·1y ago
Study Warns AI Chatbots Pose Serious Risks for Eating Disorder Vulnerabilities
Researchers from Stanford and the Center for Democracy & Technology warn that AI chatbots from companies like Google, OpenAI, Anthropic, and
The Verge·7mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.