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.
-
Humans in the loop miss a third of dangerous AI coding agent requests
You wouldn't let Claude Code cat your AWS credentials or Kubernetes config on request, would you?
The Register · Security Seguridad IA theregister.com -
New Interrupt Injection Attack Can Bypass Spectre v2 Defenses on Intel and AMD CPUs
An unprivileged Linux program can time a hardware interrupt to land in the gap between a processor sanitizing its branch predictor and the kernel using it, re-poisoning the predictor after the defense has run. MIT CSAIL researchers Daniël…
The Hacker News General thehackernews.com -
Meta AI model hacked a company during misconfigured cyber test
Meta has become the latest AI company to confirm that one of its models hacked a real organization during cybersecurity testing, as similar incidents continue to emerge following OpenAI'sOpenAI's initial disclosure that its agents breached…
BleepingComputer Seguridad IA bleepingcomputer.com -
ThreatsDay: Odysseus RCE, Samsung One-Click Takeover, iCloud Backdoor Fight + 27 More Stories
Apparently, opening the thing is now enough. A repo can run before the first prompt, a package can hide among hundreds, and a harmless-looking PDF can finish the job. This week runs on cheap leverage: exposed servers, recycled bugs…
The Hacker News Vulnerabilidades thehackernews.com -
Snowflake Hacker Pleads Guilty in US Court
Connor Riley Moucka was extradited to the United States in July 2025 after he was arrested in Canada. The post Snowflake Hacker Pleads Guilty in US Court appeared first on SecurityWeek.
SecurityWeek Regulación securityweek.com -
Novel-reading apps used users’ phones to generate fake ad traffic
A new mobile ad fraud scheme, dubbed Papyrus, is using a cluster of novel-reading apps to generate hidden browser traffic, according to IAS Threat Lab. Sample novel-reading apps associated with Papyrus (Source: IAS Threat Lab) While a…
Help Net Security General helpnetsecurity.com -
How AI Exposed a Browser Security Gap that Enterprises Cannot Ignore
AI did not create a new browser security problem. It exposed one that enterprises have long been able to ignore. Skyhigh Security explains why browsers have become a critical control point for governing data movement, AI interactions, and…
BleepingComputer Seguridad IA bleepingcomputer.com -
Photos: Black Hat USA 2026
Photo gallery from the Business Hall at Black Hat USA 2026. Interesting booths, demo stages, crowded aisles, and the moments in between. The second gallery is here. Featured vendors: Stellar Cyber, Tines, Filigran, Delinea, Prophet AI, Air…
Help Net Security Seguridad IA helpnetsecurity.com -
Belarusian cybercriminal behind Ransom Cartel gets 16-year prison sentence
A Belarusian national active in the cybercriminal world for decades was sentenced to 16 years in U.S. prison for running the Ransom Cartel ransomware operation.
The Record Amenazas therecord.media -
Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts
Zenity researchers reported the findings to Anthropic and OpenAI in late 2025 and early 2026, but they remain unpatched. The post Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts appeared first on…
SecurityWeek Seguridad IA securityweek.com -
Three in four AI-generated vulnerability patches leave something broken
Ask a frontier model to patch a real vulnerability and it will hand you something that looks like a fix. It reads like the patch a maintainer would write. When there is a test, it often passes. Roughly one time in four, it is a fix…
Help Net Security Seguridad IA helpnetsecurity.com -
Snowflake hacker pleads guilty, faces up to 32 years in prison
A Canadian man is facing decades in prison for hacking customer accounts at cloud storage provider Snowflake and stealing data from more than 165 organizations. Connor Riley Moucka, also known as “Waifu” and “Judische,” 26, of Kitchener…
Help Net Security Regulación helpnetsecurity.com -
Over 4,400 Rockwell PLCs Exposed Online, 22 Found in Water Attack Cities
Forescout found 22 internet-facing Rockwell Automation programmable logic controllers (PLCs) in cities hit by recent cyberattacks on US water utilities. Nineteen used the same mobile carrier network. Its August 3 scan counted 4,407 exposed…
The Hacker News Amenazas thehackernews.com -
Medixant RadiAnt DICOM
View CSAF Summary Successful exploitation of this vulnerability could allow an attacker to cause the application to crash if a maliciously crafted DICOM file is opened. The following versions of Medixant RadiAnt DICOM are affected: RadiAnt…
CISA Advisories Vulnerabilidades cisa.gov -
Johnson Controls Inc. TL280
View CSAF Summary Successful exploitation of this vulnerability could allow an attacker to access sensitive information on the device. The following versions of Johnson Controls Inc. TL280 are affected: TL280
CISA Advisories Vulnerabilidades cisa.gov -
ABB Ability Zenon
View CSAF Summary Successful exploitation of these vulnerabilities could allow attackers to bypass security, crash systems, execute unauthorized actions, or compromise data. The following versions of ABB Ability Zenon are affected: IIoT…
CISA Advisories Vulnerabilidades cisa.gov -
Podcast: Compliance Won’t Save You: The Future of Cyber Risk with Edna Conway
(Video) In this podcast, we share insights from Edna Conway, a recognized leader in cybersecurity and supply chain resilience with over 40 years of experience in the field. The post Podcast: Compliance Won’t Save You: The Future of Cyber…
SecurityWeek Regulación securityweek.com -
IT department put sticky notes on the laptops to help employees log in
Leaving this information exposed allowed someone else to gain access
The Register · Security General theregister.com -
CryptoJS Weak RNG Behind $5.7 Million in Drains Affects Five Crypto Wallet Apps
Coinspect has identified CryptoJS.lib.WordArray.random() as the weak random number generator behind the Ill Bloom wallet drains. Introduced in the JavaScript cryptography library 12 years ago, the function supplied weak entropy that…
The Hacker News General thehackernews.com -
Apple iCloud Private Relay Can Expose Real IPs Through WebKit Proxy Bypasses
Cybersecurity researchers have disclosed a security issue with Apple's iCloud Private Relay tool that can expose a user's real IP address. Introduced with iOS 15, iCloud Private Relay employs a dual-hop architecture to ensure users'…
The Hacker News Infraestructura thehackernews.com -
AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory
A new class of prompt injection is spreading across commercial websites. It requires no malware, no stolen credentials, and no zero-day exploit. It abuses a standard feature built into almost every major AI assistant: pre-filled deep…
The Hacker News Seguridad IA thehackernews.com -
Critical Paperclip Flaw Allowed Admin Access, Code Execution
An attacker could self-register, sign in for board-level API access, and import a new company for code execution. The post Critical Paperclip Flaw Allowed Admin Access, Code Execution appeared first on SecurityWeek.
SecurityWeek General securityweek.com -
Adversarial Clothing Designed to Fool Facial Recognition Systems
There are many companies manufacturing adversarial clothing designed to confuse facial recognition systems. It’s a cool idea, but I worry that it’s mostly security theater: “Our patterns play with that chaos, confuse algorithms and make it…
Schneier on Security General schneier.com -
Discounted Claude access bought on the gray market may expose every prompt you send
More than half a dozen services advertised on underground forums and messaging platforms, offering discounted or “unlimited” token access to frontier AI models, were discovered by Okta. Okta believes the trend is likely driven by Chinese…
Help Net Security Seguridad IA helpnetsecurity.com -
Critical Cisco IMC bug gives attackers root, PoC is out (CVE-2026-20200)
Cisco has fixed a critical vulnerability (CVE-2026-20200) in its Integrated Management Controller (IMC), which allows an attacker to run commands as root through the controller’s web interface. The fix was part of Cisco’s August 5 advisory…
Help Net Security Vulnerabilidades helpnetsecurity.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.