Hidden Commands in Images Exploit AI Chatbots and Steal Data
Hidden commands in images can exploit AI chatbots, leading to data theft on platforms like Gemini through a…
gemini
Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation
Zenity has shown how AI assistants such as ChatGPT, Copilot, Cursor, Gemini, and Salesforce Einstein can be abused using specially crafted prompts.
The post Major Enterprise AI Assistants Can Be Abused for Data Theft, Manipulation appeared first on Sec…
LegalPwn Attack Tricks GenAI Tools Into Misclassifying Malware as Safe Code
A new security flaw, LegalPwn, exploits a weakness in generative AI tools like GitHub Copilot and ChatGPT, where malicious code is disguised as legal disclaimers. Learn why human oversight is now more critical than ever for AI security.
Browser Extensions Pose Serious Threat to Gen-AI Tools Handling Sensitive Data
LayerX has disclosed an AI chatbot hacking method via web browser extensions it has named ‘man-in-the-prompt’.
The post Browser Extensions Pose Serious Threat to Gen-AI Tools Handling Sensitive Data appeared first on SecurityWeek.
Browser Extensions Can Exploit ChatGPT, Gemini in ‘Man in the Prompt’ Attack
Man in the Prompt attack shows how browser extensions can exploit ChatGPT, Gemini and other AI tools to steal data or inject hidden prompts.
ChatGPT o3 Resists Shutdown Despite Instructions, Study Claims
ChatGPT o3 resists shutdown despite explicit instructions, raising fresh concerns over AI safety, alignment, and reinforcement learning behaviors.
Google’s Sec-Gemini v1 Takes on Hackers & Outperforms Rivals by 11%
Sec-Gemini v1 has access to real-time cybersecurity data from trusted sources including Google Threat Intelligence, Mandiant’s attack reports, and the Open Source Vulnerabilities database.
Google Pushing ‘Sec-Gemini’ AI Model for Threat-Intel Workflows
Experimental Sec-Gemini v1 touts a combination of Google’s Gemini LLM capabilities with real-time security data and tooling from Mandiant.
The post Google Pushing ‘Sec-Gemini’ AI Model for Threat-Intel Workflows appeared first on SecurityWe…
Will Google Gemini Win the AI Race?
Google’s Brain Team and DeepMind have unveiled Google Gemini, a cutting-edge AI model. This remarkable system, announced by CEO Sundar Pichai, aims to revolutionize the AI industry. Combining various AI models and a massive Google dataset, Gemini has set new standards for AI capabilities. Will this versatile and powerful model win the AI race? That’s […]
The post Will Google Gemini Win the AI Race? first appeared on Internet Security Blog – Hackology.