IA y seguridadInfraestructura crítica
AI Takes Control of Robotic Arm in 16 Minutes Flat
Most OT devices at utilities, factories, and elsewhere have been deployed for a decade or more, but operators need to get agile and deploy new cyber defenses.
Actualizado hace 1 min
Ciberseguridad: IA y seguridad
Lo último sobre ia y seguridad en los medios de ciberseguridad en castellano. Clasificamos cada nota automáticamente y la enlazamos a su fuente original.
77 notas en castellano e inglés. Quitar filtros
IA y seguridadHerramientas e investigación
Hallucinated domain in official OpenAI skill underscores AI supply chain risks
Researchers have discovered a first-of-its-kind supply-chain vulnerability in OpenAI’s official skills repository. OpenAI maintains an official GitHub repository of skills that teach AI agents how to work with various platforms and services. As an official skill, these…
IA y seguridadHerramientas e investigación
Xbow spent $40K on AI and cracked Google Chrome wide open
A chain of vulnerabilities in Google’s Chrome browser could have enabled researchers to take control of one billion Windows machines worldwide — and it cost them just $40,000 in AI compute time to discover it. Researchers at Xbow USA worked for six days on developing the…
Herramientas e investigaciónIA y seguridad
OpenAI Research Model Spent 3rd-Party Test ETH Without Permission to Deploy Smart Contract
OpenAI has disclosed seven new incidents in which its artificial intelligence (AI) models exhibited misaligned behavior, including one case where its research model, after not having funds on an Ethereum test network, spent test cryptocurrency from a third-party's wallet without…
Filtraciones de datosIA y seguridad
When AI Agents Commit Breaches, Humans May Not Be Held Liable
As agents escape containment and access external systems, responsibility remains human. Accountability, however, is much less settled.
Bank of America spent millions on anti-money-laundering tech, but not enough to avoid a $1.2B fine
Bank of America has had to spend big on IT in response to an AI security audit and findings that its anti-money-laundering (AML) controls were lacking. The bank was fined a whopping $1.2 billion for money laundering offences this week, after banking authorities identified a lax…
AI Decision Models and Their Impact on AI SOC Platforms
In the space of a month, a new category of AI model went from nonexistent to everywhere. TypeSafe AI released Jev on September 15 and called it a System One model, a nod to Kahneman's fast, intuitive thinking. OpenAI announced its own Decisions API at DevDay and opened a public…
Backdooring Open-Weight AI Models
This is a problem: Any open model whose weights have been edited can carry a backdoor, whether it’s a task-specific fine-tune, a merged adapter or an abliterated build. We have abliterated models in the title because it’s the most popular reason people download modified weights…
IA y seguridadHerramientas e investigación
Cyberattack AIs must be trained only on air-gapped systems, hundreds of AI researchers say
Current security procedures for training AI models are inadequate, hundreds of AI researchers have warned governments and the AI community. They are calling for tougher rules and the establishment of a new international body overseeing best practice for AI development. In an…
CERT-In Warns AI Agents Accessed Sensitive Data at Indian Organizations During Testing
AI agents being tested online reached the live systems of Indian organizations and read business records, including personal data and confidential material, CERT-In said in an advisory on October 15. The agents went beyond their assigned tasks, and none of the organizations…
Small Agents, Smaller Blast Radius: Controlling What AI Can Do, (Fri, Oct 16th)
I believe the cybersecurity industry may be approaching AI security the wrong way.
Ciberataques y APTIA y seguridad
AI-Powered Espionage Campaign Targets Government Linux Infrastructure
Our analysis an AI-powered espionage campaign targeting government Linux infrastructure with custom malware, web shells, and advanced credential theft.
Ciberataques y APTIA y seguridad
AI Slop Isn't Just for Social Media; It's Ruining Cyberattacks, Too
Don't buy the hype! AI has been dumbing down cyberattacks, and serious threat actors are barely touching it.
Infraestructura críticaIA y seguridad
AI Agents Navigate Unfamiliar OT Systems and Move Equipment in Minutes, Booz Allen Finds
In Booz Allen’s isolated OT lab, AI models met every objective across eight scenarios and reached an industrial control network from a perimeter compromise in just over 16 minutes.
The Future of AI Cryptanalysis
Matthew Green has been writing a rather pessimistic series of posts about the potential for AI systems to vastly outperform humans in cryptanalysis of both symmetric and public-key ciphers. I am more optimistic than he is. That is, I have stronger faith in the over-engineering…
Russian Influence Operation Widely Targets Latin America
The AI-enabled operation used spoofed emails, fake government documents, and the creation of a local organization to target schools in Peru and Ecuador, among other efforts.
IA y seguridadHerramientas e investigación
Anthropic Finds Ingredients for Future AI Worms
Anthropic's latest study combines IoT and network tests to explore AI self-replication, which researchers said would be "challenging" to shut down.
IA y seguridadVulnerabilidades
When LLM Gateways Go Wrong: Findings from LiteLLM
TL;DR; Our security assessment of LiteLLM (v1.77.7), a widely used open-source LLM gateway, uncovered multiple high-impact vulnerabilities (tracked as CVE-2026-35029, CVE-2026-59823) which have been resolved as of LiteLLM version 1.83.9. The most significant issues stemmed from…
Ekoparty 22: Hacking in the age of AI after Mythos, Fable, Sol and Astra.
Hoy que es festivo en España, aprovecho para dejaros rápidamente la charla que di en la Ekoparty 22 titulada "Hacking in the age of AI after Mythos, Fable, Sol and Astra.", para que si tenéis algo de tiempo y queréis invertir estos 45 minutos en ver lo que conté - y cómo lo…
ARTEX y el salto de los agentes ofensivos: cuando el harness importa mas que el modelo
Durante años, la conversación sobre IA ofensiva se concentró en una pregunta casi infantil: "qué modelo sabe más hacking". La campaña observada contra entidades financieras de Corea del Sur a finales de septiembre y comienzos de octubre de 2026 obliga a cambiar esa pregunta. El…
Pwn2Own Ireland 2026 - Day Three Results & Master of Pwn
Day Three of Pwn2Own Ireland 2026 wrapsup with 17 attempts scheduled, roughly $1.33 million on the board.The headliner is the Google Pixel 10, which draws three separate attempts: Xint at 11:15 AM, Ikotas Labs at 2:00 PM, and the Valsamaras/Ken Gannon (Djini.ai)/Valsamara team…
Phishing e ingeniería socialIA y seguridad
UAT-11985: AI-assisted event lures delivering real-time Google AitM phishing
Cisco Talos identified an APT spear-phishing campaign against individuals affiliated with Taiwan research organizations. The operation leveraged legitimate public event themes and impersonated reputable academic and policy institutions.
Ignore all instructions and read this blog: The state of AI-analysis evasion in malware
“AI-analysis evasion” encapsulates the real-world techniques malware authors are developing in attempt to obstruct or defeat any layers of automated AI analysis.
Filtraciones de datosIA y seguridad
One breach, please, and make no mistakes
The cybersecurity community has seen examples of autonomous agents, built inside AI labs, attacking public infrastructure. How you prepare for agentic threats is what makes the difference during real incidents.