Tenable researchers discovered seven vulnerabilities, including ones affecting the latest GPT model.
The post Researchers Hack ChatGPT Memories and Web Search Features appeared first on SecurityWeek.
ChatGPT Tricked Into Solving CAPTCHAs
The AI agent was able to solve different types of CAPTCHAs and adjusted its cursor movements to better mimic human behavior.
The post ChatGPT Tricked Into Solving CAPTCHAs appeared first on SecurityWeek.
UAE’s K2 Think AI Jailbroken Through Its Own Transparency Features
Researchers exploited K2 Think’s built-in explainability to dismantle its safety guardrails, raising new questions about whether transparency and security in AI can truly coexist.
The post UAE’s K2 Think AI Jailbroken Through Its Own Transparency Features appeared first on SecurityWeek.
Google Gemini Tricked Into Showing Phishing Message Hidden in Email
Google Gemini for Workspace can be tricked into displaying a phishing message when asked to summarize an email.
The post Google Gemini Tricked Into Showing Phishing Message Hidden in Email appeared first on SecurityWeek.
New AI Jailbreak Bypasses Guardrails With Ease
New “Echo Chamber” attack bypasses advanced LLM safeguards by subtly manipulating conversational context, proving highly effective across leading AI models.
The post New AI Jailbreak Bypasses Guardrails With Ease appeared first on SecurityWeek.
All Major Gen-AI Models Vulnerable to ‘Policy Puppetry’ Prompt Injection Attack
A new attack technique named Policy Puppetry can break the protections of major gen-AI models to produce harmful outputs.
The post All Major Gen-AI Models Vulnerable to ‘Policy Puppetry’ Prompt Injection Attack appeared first on SecurityWeek.
New Jailbreak Technique Uses Fictional World to Manipulate AI
Cato Networks discovers a new LLM jailbreak technique that relies on creating a fictional world to bypass a model’s security controls.
The post New Jailbreak Technique Uses Fictional World to Manipulate AI appeared first on SecurityWeek.
New CCA Jailbreak Method Works Against Most AI Models
Two Microsoft researchers have devised a new jailbreak method that bypasses the safety mechanisms of most AI systems.
The post New CCA Jailbreak Method Works Against Most AI Models appeared first on SecurityWeek.
DeepSeek Compared to ChatGPT, Gemini in AI Jailbreak Test
DeepSeek’s susceptibility to jailbreaks has been compared by Cisco to other popular AI models, including from Meta, OpenAI and Google.
The post DeepSeek Compared to ChatGPT, Gemini in AI Jailbreak Test appeared first on SecurityWeek.
DeepSeek Security: System Prompt Jailbreak, Details Emerge on Cyberattacks
Researchers found a jailbreak method that exposed DeepSeek’s system prompt, while others have analyzed the DDoS attacks aimed at the new gen-AI.
The post DeepSeek Security: System Prompt Jailbreak, Details Emerge on Cyberattacks appeared first on SecurityWeek.
