Study shows poetic prompts could cause AI to jailbreak
By Christianna Silva Publication Date: 2025-12-05 20:16:00 Well, AI joins many, many people: it doesn’t really understand poetry. Research from…
Tag: Jailbreak
Researchers Find Easy Way to Jailbreak Every Major AI, From ChatGPT to Claude
Security researchers have discovered a highly effective new jailbreak that can dupe nearly every major large language model into producing…
New Jailbreak Technique Uses Fictional World to Manipulate AI – SecurityWeek
New Jailbreak Technique Uses Fictional World to Manipulate AI SecurityWeek Article Source https://www.securityweek.com/new-jailbreak-technique-uses-fictional-world-to-manipulate-ai/
‘You can now jailbreak your AMD CPU’ — Google researchers release kit to exploit microcode vulnerability in Ryzen Zen 1 to Zen 4 chips
A team of Google researchers working with AMD recently discovered a major CPU exploit on Zen-based processors. The exploit allows…
This Week In Security: Zen Jailbreak, Telegram Exploit, And VMware Hyperjack
The fine researchers at Google have released the juicy details on EntrySign, the AMD Zen microcode issue we first covered…
Jailbreak Anthropic's new AI safety system for a $15,000 reward
MirageC/Getty Images Can you jailbreak Anthropic’s latest AI safety measure? Researchers want you to try — and are offering up…
Anthropic dares you to jailbreak its new AI model
An example of the lengthy wrapper the new Claude classifier uses to detect prompts related to chemical weapons. An example…
Researchers say they had a ‘100% attack success rate’ on jailbreak attempts against Chinese AI startup DeepSeek
Researchers say they had a ‘100% attack success rate’ on jailbreak attempts against Chinese AI startup DeepSeek Fortune Article Source https://fortune.com/2025/02/02/deepseek-ai-chatbot-security-jailbreak-attempts-openai-cisco/
Deepseek's AI model proves easy to jailbreak – and worse
goc/Getty Images Amidst equal parts elation and controversy over what its performance means for AI, Chinese startup DeepSeek continues to…