Radar de seguridad e inteligencia artificial
Noticias
Revisamos cada hora los feeds públicos de 60 fuentes de referencia y clasificamos cada titular por tema y severidad. Aquí verás el titular y un extracto breve: la noticia se lee en su fuente original.
en 24 horas
semana
crítica
en seguimiento
Actualización horaria Última revisión hace 14 min 959 titulares en el archivo
Qué se está publicando
Distribución por tema
78 titulares en Seguridad IA de severidad Media Limpiar filtros ×
- lunes 10 ago
-
OpenAI releases ChatGPT 5.6 Cyber, but it's only for approved users
OpenAI has developed a new model called "GPT 5.6 Cyber," designed for vulnerability research, penetration testing, incident response, and remediation. [...]
BleepingComputer Seguridad IA bleepingcomputer.com -
North Korean spies are running local LLMs to cause AI mischief
Kimsuky's phishing attacks get an AI boost
The Register · Security Seguridad IA theregister.com -
Microsoft named a Leader in the 2026 IDC MarketScape for MDR/MXDR for the Enterprise
Microsoft is named a Leader in the 2026 IDC MarketScape for MDR services. Discover how Microsoft Defender Experts MDR combines AI, threat intelligence, and human expertise. The post Microsoft named a Leader in the 2026 IDC MarketScape for…
Microsoft Security Blog Seguridad IA microsoft.com - domingo 9 ago
-
The Hugging Face Hack Was Cheap Persistence at Work
The Hugging Face and OpenAI security incident showed AI doesn't make attackers smarter. It makes persistence cheap, and defenses built for alerts can't keep up.
Recorded Future Seguridad IA recordedfuture.com - miércoles 5 ago
-
Can AI do novel security research? Meet the HTTP Terminator
Abstract We all know AI can find bugs. After a decade of research, I asked a harder question: can an autonomous system invent new attack techniques, and use them to hack live websites at scale? Buildi
PortSwigger Research Seguridad IA portswigger.net - martes 4 ago
-
A First Look at Evo Agentic AppSec: Agentic Remediation and Malicious Code Defense
Explore Snyk’s first Agentic AppSec capabilities: an autonomous Remediation Agent that fixes vulnerabilities and Malicious Code Defense that blocks risky packages before they ship.
Snyk Seguridad IA snyk.io - jueves 30 jul
-
A hole in every one: bypassing the open source AI skill scanners
We ran eight open source AI skill scanners against real attacks. A malicious skill got past all eight, including the current OASB leaderboard leader.
Adversa AI Seguridad IA adversa.ai -
Escaping Linux Sandboxes via PipeWire (CVE-2026-5674)
This post walks through a sandbox escape from a Flatpak application via PipeWire. The vulnerability was discovered using my automated research pipeline with Claude Code and Opus 4.6 back in April 2026. It was an exciting find, as this was…
Embrace The Red Seguridad IA embracethered.com - martes 28 jul
-
How we use /goal to find bugs in Patch the Planet
Codex’s /goal feature amplifies bug hunting, but getting good results requires the right prompt, the right scope, and the right number of outcomes per run. For Patch the Planet, our joint initiative with OpenAI to find and fix bugs in…
Trail of Bits Seguridad IA blog.trailofbits.com - miércoles 22 jul
-
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 - miércoles 8 jul
-
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 - miércoles 1 jul
-
Silver Bullet Security Podcast 158 – Artem Dinaburg
View on Zencastr On Episode 158 of the Silver Bullet Security Podcast, BIML’s Gary McGraw hosts Artem Dinaburg. Artem talks about using Agentic AI to find, fix, and exploit software security defects. We talk decompilation, stochasticism…
Berryville Institute (BIML) Seguridad IA berryvilleiml.com - jueves 25 jun
-
Computer-Use and TOCTOU: What You Click Is Not What You Get!
Last year, Jun Kokatsu disclosed an interesting vulnerability with ChatGPT Operator by exploiting a race condition. I was wondering if I could reproduce this attack chain, and this post describes the results of that research. I had this…
Embrace The Red Seguridad IA embracethered.com - lunes 4 may
-
Copirate 365 at DEF CON: Plundering in the Depths of Microsoft Copilot (CVE-2026-24299)
This is a writeup of my DEF CON Singapore talk that walks through vulnerabilities and exploits in M365 Copilot and Consumer Copilot. I disclosed these to Microsoft last year. MSRC assigned CVE-2026-24299 and the issues are now patched…
Embrace The Red Seguridad IA embracethered.com - viernes 17 abr
-
Breaking Opus 4.7 with ChatGPT (Hacking Claude's Memory)
In this post, we explore how ChatGPT generated an adversarial image that hijacked my Claude Opus 4.7 to invoke the memory tool and persist false memories for future chats. This matters because Opus 4.6+ is genuinely a lot harder to attack…
Embrace The Red Seguridad IA embracethered.com - jueves 2 abr
-
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 - miércoles 11 mar
-
Windows and macOS Malware Spreads via Fake “Claude Code” Google Ads
Bitdefender’s security researchers have discovered a malicious Google Ads campaign targeting anyone searching for downloads related to Claude, the large language model developed by Anthropic.
Bitdefender Labs Seguridad IA bitdefender.com
Del titular al control
Leer noticias no reduce el riesgo
En el blog publicamos análisis propios que traducen esto en decisiones: qué controlar primero, con qué evidencia y en qué orden.