Generative AI

Generative AI | News, how-tos, features, reviews, and videos

NIST’s attempts to secure AI yield many questions, no answers

A NIST AI concept paper details the key enterprise security challenges and asks for industry comments. But what if AI agents flood the comments with their own self-preservation suggestions?

Aug 19, 2025 9 mins

Artificial Intelligence Generative AI Security

GPT-5 jailbroken hours after launch using ‘Echo Chamber’ and Storytelling exploit

NeuralTrust says GPT-5 was jailbroken within hours of launch using a blend of ‘Echo Chamber’ and storytelling tactics that hid malicious goals in harmless-looking narratives.

Aug 12, 2025 4 mins

Generative AI Security Vulnerabilities

Black Hat: Researchers demonstrate zero-click prompt injection attacks in popular AI agents

Researchers from Zenity have found multiple ways to inject rogue prompts into agents from mainstream vendors to extract sensitive data from linked knowledge sources.

Aug 8, 2025 8 mins

Cyberattacks Events Generative AI

Black Hat 2025 Recap: A look at new offerings announced at the show

AI dominated the conversation at Black Hat 2025, from the rise of autonomous agents and shadow AI to surging identity-based attacks and hardware-level exploits, and product announcements reflected that trend.

Aug 7, 2025 7 mins

Artificial Intelligence Events Generative AI

Anthropic targets DevSecOps with Claude Code update as AI rivals gear up

With GPT-5 on the horizon and Meta ramping up AI hiring, Anthropic’s new security-focused features aim to differentiate Claude in the increasingly crowded GenAI coding space.

Aug 7, 2025 1 min

Engineer Generative AI Security

How cybersecurity leaders are securing AI infrastructures

AI models, agentic frameworks, data pipelines, and all the tools, services, and open-source libraries that make AI possible are evolving quickly and cybersecurity leaders must be on top of it.

Aug 6, 2025 10 mins

Artificial Intelligence Generative AI Security Infrastructure

MCP: securing the backbone of Agentic AI

MCP makes agentic AI flexible - but also vulnerable. For CISOs, visibility, control and secure workflows are crucial for trust and resilience.

Aug 4, 2025 6 mins

Generative AI

Google Gemini vulnerability enables hidden phishing attacks

A bug in Google Gemini allows attackers to hijack email summaries and launch phishing attacks.

Jul 15, 2025 3 mins

Generative AI Network Security Zero-Day Vulnerabilities

Critical RCE flaw in Anthropic’s MCP inspector exposes developer machines to remote attacks

A misconfigured default in the MCP inspector tool allows attackers to execute arbitrary commands via CSRF and legacy browser flaws, posing serious risks to AI developers and enterprise systems.

Jul 2, 2025 4 mins

Engineer Generative AI Vulnerabilities

How cybersecurity leaders can defend against the spur of AI-driven NHI

Non-human identities were already a challenge for security teams before AI agents came into the picture. Now, companies that haven't come to grips with this problem will see it become even more critical.

Jul 2, 2025 12 mins

Generative AI Identity Management Solutions Identity and Access Management