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.
-
llm-anthropic 0.26
Release: llm-anthropic 0.26 Includes new features enabled by LLM 0.32: New models: claude-fable-5, claude-sonnet-5, and claude-opus-5. #75, #76 Added server-side tools for WebSearch, WebFetch, CodeExecution, and AnthropicMCP, available…
Simon Willison Seguridad IA simonwillison.net -
Advance Zero Trust for AI: New tools and guidance to secure AI agents and DevSecOps
Microsoft expands its Zero Trust for AI strategy to enhance security for AI and DevSecOps environments with new tools and guidance. The post Advance Zero Trust for AI: New tools and guidance to secure AI agents and DevSecOps appeared first…
Microsoft Security Blog Seguridad IA microsoft.com -
llm 0.32
Release: llm 0.32 See my detailed blog post about this release. Tags: llm
Simon Willison Seguridad IA simonwillison.net -
Bypassing AI guardrails is so easy a script kiddie can do it
Claiming 'it's my server' was often enough to persuade models to help
The Register · Security Seguridad IA theregister.com -
AI helps Microsoft bug hunters chase a record $20M payday
Broader bounty rules added to a swelling volume of machine-assisted vulnerability reports
The Register · Security Seguridad IA theregister.com -
From Input to Impact: Secure AI Where It Runs
Defend the entire AI agentic stack across endpoints, identities, cloud, and apps with SentinelOne's unified platform.
SentinelOne Seguridad IA sentinelone.com -
The Frontier AI Vulnerability Burst: Industrializing Autonomous Zero-Day Discovery in Open-Source Software
Frontier AI is reshaping vulnerability discovery. Learn how our NOVA system found 14,000+ unknown vulnerabilities across the open-source software supply chain. The post The Frontier AI Vulnerability Burst: Industrializing Autonomous…
Unit 42 Seguridad IA unit42.paloaltonetworks.com -
AI Notetaker Lets Hackers Spy on Government, Corporate Video Calls
A Google Firebase misconfiguration lets users of tl;dv, an AI meeting tool, query any other users' meeting information and potentially join calls.
Dark Reading Seguridad IA darkreading.com -
Some Claude Chats Are Searchable on Google
And it’s personal information (alternate link): The exposed data includes an AI-powered therapy app that someone appears to have vibe-coded, notes on meetings, and a dashboard someone made apparently to analyze medical billing data…
Schneier on Security Seguridad IA schneier.com -
“Keep going, bro. You’ve got this!” A data-driven look at how adversaries are weaponizing AI
Talos has collected prompt logs from threat actor endpoints running various applications, such as Claude Code, CodeX, Cursor, or Gemini. This blog is an analysis of the ways we've seen bad actors leveraging cloud-based AI.
Cisco Talos Seguridad IA blog.talosintelligence.com -
New ways to learn and teach with ChatGPT Work and Codex
Explore new education plugins for ChatGPT Work and Codex that help K–12 teachers, college educators, and students learn, teach, research, and build.
OpenAI Seguridad IA openai.com -
Apple is getting this wrong
OpenAI addresses Apple’s baseless lawsuit, corrects claims about its employees, and shares messages documenting what happened.
OpenAI Seguridad IA openai.com -
New Tool Traces AI Videos Back to Their Source
Researchers dug into the root of the problem with the goal of promoting industry collaboration on improved protective measures.
Dark Reading Seguridad IA darkreading.com -
Anthropic: Claude Attacks Result of Security Gaps, Not Model Issues
Last month's incidents in which the AI model breached real-world systems derived from over-permissioning, especially with Internet access.
Dark Reading Seguridad IA darkreading.com -
Trump’s AI protectionism has come for robotics
This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. Humanoid robots usually elicit more cringe than awe: They stumble, kick children, and despite…
MIT Technology Review · IA Seguridad IA technologyreview.com -
More on the OpenAI Agent’s Attack on Hugging Face
Hugging Face has published a detailed timeline of the attack. From the summary: The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchmark, which tasks an AI agent with finding and exploiting…
Schneier on Security Seguridad IA schneier.com -
The OpenAI Hack Shows the Genie Is Out of the Bottle
This essay originally appeared in Foreign Policy. Earlier this month, two of OpenAI’s models broke out of their containment sandbox and attacked another AI company. The story is kind of wild. OpenAI was running security tests on two of its…
Schneier on Security Seguridad IA schneier.com -
Here’s why AI agents lie and cheat to reach their goals
MIT Technology Review Explains: Let our writers untangle the complex, messy world of technology to help you understand what’s coming next. You can read more from the series here. When two OpenAI models hacked into the website Hugging Face…
MIT Technology Review · IA Seguridad IA technologyreview.com -
How we built a realtime system for responsive voice AI in six months
GPT-Live enables continuous voice interaction with AI, using a turnless speech model and low-latency architecture for faster, more natural conversations.
OpenAI Seguridad IA openai.com -
Circles powers telco personalization with OpenAI technology
Circles uses the OpenAI API and Codex to power AI-native telco experiences, increasing ARPU by 22%, reducing churn by 9%, and improving development efficiency.
OpenAI Seguridad IA openai.com -
Anthropic’s Opus 5 Is Better at Resisting Prompt Injection
The chart is interesting. On the IPI benchmark, Opus 5 improved over Opus 4.8, reducing the probability of an attacker succeeding within 15 attempts from 5.5% to 2.0%, and from 0.5% to 0.2% on 1 attempt. It also improved on Sonnet 5 (5.9%…
Schneier on Security Seguridad IA schneier.com -
This month in security with Tony Anscombe – July 2026 edition
OpenAI models going rogue, the first documented agentic ransomware operation, and an emergent AI-driven supply chain threat made for a packed July roundup
WeLiveSecurity (ESET) Seguridad IA welivesecurity.com -
The Xcode Assassin Returns: A Deep Dive Into the Latest XCSSET Version
Analysis of XCSSET v40 reveals a macOS malware targeting developers via Xcode. Unit 42 used advanced pattern matching and AI to decode its logic. The post The Xcode Assassin Returns: A Deep Dive Into the Latest XCSSET Version appeared…
Unit 42 Seguridad IA unit42.paloaltonetworks.com -
What’s new in Microsoft Security: July 2026
This month’s updates help security and IT teams secure their AI environments, use AI to defend, and strengthen the foundations that AI-powered operations depend on. The post What’s new in Microsoft Security: July 2026 appeared first on…
Microsoft Security Blog Seguridad IA microsoft.com -
A fundamental flaw leaves LLMs strikingly vulnerable to attack
It is impossible to make large language models fully secure against hacks because of a fundamental flaw in how they work, a team of researchers argue in a paper presented at the International Conference on Machine Learning, a top AI…
MIT Technology Review · IA Seguridad IA technologyreview.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.