Proof-of-concept ransomware uses AI models to generate attack scripts in real time.
The post PromptLock: First AI-Powered Ransomware Emerges appeared first on SecurityWeek.
Beyond the Prompt: Building Trustworthy Agent Systems
Building secure AI agent systems requires a disciplined engineering approach focused on deliberate architecture and human oversight.
The post Beyond the Prompt: Building Trustworthy Agent Systems appeared first on SecurityWeek.
AI Systems Vulnerable to Prompt Injection via Image Scaling Attack
Researchers show how popular AI systems can be tricked into processing malicious instructions by hiding them in images.
The post AI Systems Vulnerable to Prompt Injection via Image Scaling Attack appeared first on SecurityWeek.
Managing the Trust-Risk Equation in AI: Predicting Hallucinations Before They Strike
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.
Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise
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.
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 SecurityWeek.
Vibe Coding: When Everyone’s a Developer, Who Secures the Code?
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.
Microsoft Offers $5 Million at Zero Day Quest Hacking Contest
Research demonstrating high-impact cloud and AI security flaws will be rewarded at Microsoft’s Zero Day Quest competition in spring 2026.
The post Microsoft Offers $5 Million at Zero Day Quest Hacking Contest appeared first on SecurityWeek.
Nvidia Triton Vulnerabilities Pose Big Risk to AI Models
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.
AI Guardrails Under Fire: Cisco’s Jailbreak Demo Exposes AI Weak Points
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.
