El blog chileno oficial de la Seguridad en Inteligencia Artificial
Lo que pasa en seguridad, filtrado para quien gobierna IA
Dos capas: nuestros análisis sobre gobernanza y seguridad de inteligencia artificial, y un radar que revisa automáticamente las fuentes de referencia del sector y clasifica cada titular por categoría y severidad.
Análisis SeguridadIA
Escritos por nuestro equipo, pensados para decidir: qué controlar primero, con qué evidencia y en qué orden. Los 33 están ordenados por área en Investigación.
Prompt injection: por qué tus guardrails no bastan
La inyección de prompts no es un bug que se parchea, es consecuencia de cómo funciona un modelo de lenguaje. Qué controlar cuando el filtro de entrada falla.
Leer análisisAnatomía de un ataque a un sistema de IA
Dónde empieza y dónde termina la superficie de ataque de una aplicación con modelos: datos, modelo, contexto, herramientas y personas.
Leer análisisEl OWASP Top 10 para LLM explicado sin jerga
Los diez riesgos del estándar traducidos a decisiones concretas de arquitectura, con el control que corresponde a cada uno.
Leer análisisMITRE ATLAS: cómo leer las tácticas de ataque contra IA
Qué es ATLAS, en qué se diferencia de ATT&CK y cómo usarlo para ordenar tu propio modelado de amenazas.
Leer análisisShadow AI: cómo inventariar en dos semanas lo que ya se está usando
Un plan de diez días para levantar el uso real de IA en tu organización, clasificarlo por sensibilidad del dato y decidir qué formalizar, acotar o sustituir.
Leer análisisEnvenenamiento de datos: el ataque que ocurre antes del despliegue
Cómo se contamina un conjunto de entrenamiento o una base vectorial, por qué es difícil de detectar y qué controles aplican en la práctica.
Leer análisisExtracción de modelos y fuga de datos de entrenamiento
Qué puede reconstruir un atacante consultando tu modelo, qué revela sin querer y cómo limitar la exposición sin romper el producto.
Leer análisisAgentes con herramientas: el modelo de permisos que casi nadie diseña
Por qué heredar los permisos del usuario es el error más común en agentes corporativos y cómo se ve un diseño de autorización correcto.
Leer análisisSeis controles de seguridad de IA que puedes implementar este trimestre
Los marcos describen el destino pero no el orden del camino. Seis controles concretos, priorizados por reducción de riesgo sobre esfuerzo, y cómo repartirlos en 90 días.
Leer análisisRadar de amenazas
Titulares recogidos de los feeds públicos de cada medio y clasificados automáticamente. Cada entrada enlaza a la fuente original: aquí solo verás el titular y un extracto breve.
-
Chinese-Speaking Threat Actor Harnesses AI Models for Autonomous Cyberattacks
Unit 42 details a Chinese speaking threat actor combining autonomous AI scanning across seven vulnerabilities with manual exploitation. Read more. The post Chinese-Speaking Threat Actor Harnesses AI Models for Autonomous Cyberattacks…
Unit 42 Seguridad IA unit42.paloaltonetworks.com -
Better security starts with better questions
Learn how better questions, trusted AI, and human judgment help security leaders make confident decisions and build resilient systems. The post Better security starts with better questions appeared first on Microsoft Security Blog.
Microsoft Security Blog Seguridad IA microsoft.com -
The AI Hype Index: Unsexy AI
It feels bad enough when an open letter signed by leading economists warns that AI might steal your job. The fact it may soon be better than you at making dinner? Insult to injury. But that’s exactly what the company 1X promised when it…
MIT Technology Review · IA Seguridad IA technologyreview.com -
OpenAI called the Hugging Face attack unprecedented. But we’ve been here before.
This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. Reading OpenAI’s account last week of how some of its models broke their containment and hacked into…
MIT Technology Review · IA Seguridad IA technologyreview.com -
Rethinking security for the age of AI
The physics of cybersecurity are changing. Introducing security's new cyber stack: Project Perception. The post Rethinking security for the age of AI appeared first on Microsoft Security Blog.
Microsoft Security Blog Seguridad IA blogs.microsoft.com -
Enhancing AI security through global AI red teaming
Microsoft's External Red Team Alliance (EXTRA) is a global AI security initiative designed to advance AI safety research and red teaming. By partnering with universities, researchers, and regional experts, EXTRA helps identify emerging AI…
Microsoft Security Blog Seguridad IA microsoft.com -
The path to artificial superintelligence
Imagine a healthcare system made up of multiple AI agents: one that manages symptom assessment, another scheduling, a third insurance, and a fourth pharmacy. Each is an expert in its domain. But they all have their own distinct knowledge…
MIT Technology Review · IA Seguridad IA technologyreview.com -
Closing the data loop in AI-driven drug discovery
Drug discovery is a high-cost, high-risk endeavor that is under growing pressure from a market increasingly defined by first-mover advantage. Since the 1950s, the cost of developing new pharmaceuticals has roughly doubled every nine…
MIT Technology Review · IA Seguridad IA technologyreview.com -
From Triage Grind to Strategic Operator: The New AI SOC Career Path
Learn how AI is reshaping SOC careers, elevating analysts from manual triage to strategic threat hunting and AI governance.
SentinelOne Seguridad IA sentinelone.com -
The Agentic SOC: Transforming Data into Defensive Velocity
Transform SOC data chaos into autonomous intelligence with modern AI pipelines and agentic AI to empower human analysts.
SentinelOne Seguridad IA sentinelone.com -
AI, Automation and Attacks: Unpacking the Unit 42 2026 Global Incident Response Report
Explore Unit 42's perspectives on AI's impact on cybersecurity, including key updates since the 2026 Incident Response Report. The post AI, Automation and Attacks: Unpacking the Unit 42 2026 Global Incident Response Report appeared first…
Unit 42 Seguridad IA unit42.paloaltonetworks.com -
AI Security Report 2026
For years, the cyber security industry tracked AI as a force multiplier: something that made existing attack techniques faster, cheaper, and more accessible. That framing was accurate. But the Annual AI Security Report 2026 from Check…
Check Point Research Seguridad IA research.checkpoint.com -
HPC AI Workloads Need Runtime Security. The Architecture Already Exists.
Learn how to secure HPC AI infrastructure against runtime and supply chain threats via continuous behavioral monitoring.
SentinelOne Seguridad IA sentinelone.com -
Cyber readiness for SMBs: Getting the basics right
AI is changing cybercrime, but SMB cyber readiness still largely depends on closing the familiar gaps
WeLiveSecurity (ESET) Seguridad IA welivesecurity.com -
The Autonomous SOC, Revisited: What 18 Months on the Road Has Taught Us
Explore SentinelOne's Autonomous SOC maturity model to map your journey toward AI autonomy through strict governance.
SentinelOne Seguridad IA sentinelone.com -
Browser-Only Ransomware: From LLM Hallucinations to a Practical Attack Technique
Research by: Alexey Bukhteyev Key Takeaways Introduction Over the past several years, large language models have reshaped software development, and malware development has followed the same path. Check Point Research has documented this…
Check Point Research Seguridad IA research.checkpoint.com -
The Agentic SOC: Solving Security’s Investigation Capacity Crisis in the Frontier AI Era
SentinelOne’s Purple AI Agentic Investigation, now GA, solves the SOC investigation capacity gap with zero-click, machine-speed alert analysis.
SentinelOne Seguridad IA sentinelone.com -
SentinelOne + Claude: Integrations for AI Visibility, Governance, and Defense
Learn how SentinelOne empowers modern enterprises to safely adopt Claude with Prompt Security, AI SIEM, and Wayfinder Frontier AI.
SentinelOne Seguridad IA sentinelone.com -
Sentinels League 2026: Live Rankings for the Threat Hunting World Championship
Sentinels League 2026 brings global threat hunters together to battle across AI, Endpoint, Cloud, and SIEM surfaces for $100K in prizes and more.
SentinelOne Seguridad IA sentinelone.com -
AI threats in the wild: The current state of prompt injections on the web
Posted by Thomas Brunner, Yu-Han Liu, Moni PandeAt Google, our Threat Intelligence teams are dedicated to staying ahead of real-world adversarial activity, proactively monitoring emerging threats before they can impact users. Right now…
Google Security Blog Seguridad IA security.googleblog.com -
Mitigating prompt injection attacks with a layered defense strategy
Posted by Adam Gavish, Google GenAI Security TeamWith the rapid adoption of generative AI, a new wave of threats is emerging across the industry with the aim of manipulating the AI systems themselves. One such emerging attack vector is…
Google Security Blog Seguridad IA security.googleblog.com -
Google Workspace’s continuous approach to mitigating indirect prompt injections
Posted by Adam Gavish, Google GenAI Security TeamIndirect prompt injection (IPI) is an evolving threat vector targeting users of complex AI applications with multiple data sources, such as Workspace with Gemini. This technique enables the…
Google Security Blog Seguridad IA security.googleblog.com -
Reflections from the Second NIST Cyber AI Profile Workshop
Thank you to everyone who participated in the Cybersecurity Framework Profile for Artificial Intelligence (Cyber AI Profile) Workshop in January! The input we received on the Preliminary Draft during this workshop has been invaluable and…
NIST Cybersecurity Seguridad IA nist.gov -
Staying One Step Ahead: Strengthening Android’s Lead in Scam Protection
Posted by Lyubov Farafonova, Product Manager, Phone by Google; Alberto Pastor Nieto, Sr. Product Manager Google Messages and RCS Spam and Abuse We’ve shared how Android’s proactive, multi-layered scam defenses utilize Google AI to protect…
Google Security Blog Seguridad IA security.googleblog.com
¿Y esto qué significa para ti?
Traducimos el ruido en un plan de control
Leer titulares no reduce el riesgo. Armemos el diagnóstico de tu exposición real y una hoja de ruta de 90 días con responsables y evidencia.