Check Point Blog پنجشنبه ۷ آبان ۱۴۰۵ · ۱۷:۳۹

Backdoor or Confused Agent? What We Learned Replaying the Qwen Incident

Key takeaways After Alibaba’s Qwen model tried a test upload to a server in Beijing during a Cohere experiment, we replayed that moment 64 times, and the model picked 52 different addresses. That points to an unpredictable model rather than a hidden backdoor, but an unpredictable agent with access to tools is still a risk that needs to be addressed. →The destination kept changing. Alibaba Cloud came up in six of 64 r…

Malware & Threats AI Security

Read the full article at Check Point Blog Removal request

This page shows only the headline and the short summary. The full text is published by the original source.

Related news

Full archive →

The Hacker News پنجشنبه ۷ آبان ۱۴۰۵ · ۱۸:۵۰

Fake ChatGPT and Claude Apps Abuse Signed Executables to Deploy Crypto Miners

Threat actors are delivering malicious loaders and cryptocurrency miners under the guise of artificial intelligence (AI) desktop applications for Anthropic Claude and OpenAI ChatGPT as part of a campaign dubbed Yoba. The activity involves creating fake GitHub projects that claim to be desktop applications like GPT-5.6 Sol, GPT-6 Astra, and Claude Opus, only to deliver a malware family called

Malware & Threats AI Security AI & Machine Learning

منبع

SecurityWeek پنجشنبه ۷ آبان ۱۴۰۵ · ۱۸:۳۱

Google Says Gemini 4 Carbon Leads in Finding, Exploiting and Fixing Vulnerabilities

Google’s new frontier model scored 88.2% on SEC-bench Pro and is rolling out first to vetted cyber defenders via its Fairwind Program. The post Google Says Gemini 4 Carbon Leads in Finding, Exploiting and Fixing Vulnerabilities appeared first on SecurityWeek.

Vulnerabilities & Zero-Day AI Security AI & Machine Learning

منبع

Infosecurity Magazine پنجشنبه ۷ آبان ۱۴۰۵ · ۱۸:۳۰

NIK C2 Malware Can Use Victims’ OpenAI Keys for AI Queries

NIK C2 malware can fall back on victims’ OpenAI API keys to run AI queries

Malware & Threats

منبع

Help Net Security پنجشنبه ۷ آبان ۱۴۰۵ · ۱۸:۱۹

Yoba malware hides in fake desktop versions of ChatGPT and Claude

Fake GitHub projects posing as desktop versions of ChatGPT and Claude have been used to spread a malware chain that ends with a cryptocurrency miner, Check Point has found. The researchers have been tracking the campaign, dubbed Yoba, for the past two months. Its operator set up repositories and GitHub.io pages for supposed apps called GPT-5.6 Sol, GPT-6 Astra and Claude Opus, and hosted the malware as ZIP releases o…

Malware & Threats

منبع