Instead of GPT-5 Pro, your query could be quietly redirected to an older, weaker model, opening the door to jailbreaks, hallucinations, and unsafe outputs.
The post GPT-5 Has a Vulnerability: Its Router Can Send You to Older, Less Safe Models appeared first on SecurityWeek.
New physics-based research suggests large language models could predict when their own answers are about to go wrong — a potential game changer for trust, risk, and security in AI-driven systems.
The post Managing the Trust-Risk Equation in AI: Predicting Hallucinations Before They Strike appeared first on SecurityWeek.
Researchers demonstrate how multi-turn “storytelling” attacks bypass prompt-level filters, exposing systemic weaknesses in GPT-5’s defenses.
The post Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise appeared first on SecurityWeek.
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 SecurityWeek.
As AI makes software development accessible to all, security teams face a new challenge: protecting applications built by non-developers at unprecedented speed and scale.
The post Vibe Coding: When Everyone’s a Developer, Who Secures the Code? appeared first on SecurityWeek.
Nvidia has patched over a dozen vulnerabilities in Triton Inference Server, including another set of vulnerabilities that threaten AI systems.
The post Nvidia Triton Vulnerabilities Pose Big Risk to AI Models appeared first on SecurityWeek.
Cisco’s latest jailbreak method reveals just how easily sensitive data can be extracted from chatbots trained on proprietary or copyrighted content.
The post AI Guardrails Under Fire: Cisco’s Jailbreak Demo Exposes AI Weak Points appeared first on SecurityWeek.
Noma Security has announced a Series B funding round that will enable the company’s growth and expansion of its AI agent security solutions.
The post Noma Security Raises $100 Million for AI Security Platform appeared first on SecurityWeek.
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.
The Israeli startup helps organizations identify, monitor, and control AI agents across their environments.
The post Cyata Emerges From Stealth With $8.5 Million in Funding appeared first on SecurityWeek.
