The Hacker News

Traditional Security Frameworks Leave Organizations Exposed to AI-Specific Attack Vectors

AI-driven attacks leaked 23.77 million secrets in 2024, revealing that NIST, ISO, and CIS frameworks lack coverage for ...
MediaNama

Explained: How Prompt Injections Put AI Browsers Like ChatGPT Atlas At Risk

Read how prompt injection attacks can put AI-powered browsers like ChatGPT Atlas at risk. And what OpenAI says about combatting them.
eWeek

OpenAI Steps Up Security as ChatGPT Atlas Faces Ongoing Prompt Injection Threats

The AI firm has rolled out a new security update to Atlas’ browser agent after uncovering a new class of prompt injection ...
eWeek

LangChain AI Vulnerability Exposes Millions of Apps

A critical LangChain AI vulnerability exposes millions of apps to theft and code injection, prompting urgent patching and ...
Security Boulevard

Threat Detection Software: The Complete Guide to Protecting Your Digital Assets in 2026

The cybersecurity landscape in 2026 presents unprecedented challenges for organizations across all industries. With ...

AIブラウザ「ChatGPT Atlas」では「勝手に辞職メールを送信」など有害 ...

OpenAIが2025年10月にリリースしたウェブブラウザ「ChatGPT Atlas」にはAIエージェントが組み込まれており、情報収集やメール処理などの作業をAIに実行させることができます。そんなChatGPT ...
Opinion

Red teaming LLMs exposes a harsh truth about the AI security arms race

Every frontier model breaks under sustained attack. Red teaming reveals the gap between offensive capability and defensive readiness has never been wider.