Español

Explorar

Noticias de IA

1359 elementos — filtrados, clasificados y sin duplicados

Todos Models & Releases Research & Papers Funding & M&A Policy & Regulation Product Launches Industry Moves Developer Tooling Opinion & Editorial Security & Safety Other
arXiv cs.AI Security & Safety
XAI-SDN: An Explainable Entropy-Guided Machine Learning Framework for Real-Time DDoS Dete…
arXiv cs.AI Security & Safety
From Review to Authorization: Key-Isolated Threshold Signing for LLM Agents
arXiv cs.AI Security & Safety
Beyond the Verdict: Evidence-Aligned Evaluation of Visual Prompt-Injection Guardrails
arXiv cs.AI Security & Safety
Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning
arXiv cs.AI Security & Safety
SRD-GUARD: A Defense Framework of LLMs via Semantic Rewriting and Joint Multi-Model Scori…
arXiv cs.AI Security & Safety
A TTP by TTP Approach: Precise Malware Detection via Malicious TTP Recognition
arXiv cs.AI Security & Safety
WolfSociety: Understanding Collective Risk from Harmful-Agent Scaling in Financial Agent …
arXiv cs.AI Security & Safety
D-ADD: An Effective Plug-In for Defending Against Model Stealing
arXiv cs.AI Security & Safety
Structurally Close, Temporally Distant: Measuring Security Exposure in Long-Horizon LLM A…
arXiv cs.AI Security & Safety
Staying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testi…
Bloomberg Technology Security & Safety
Cisco President on Defending Against AI Attacks
Ars Technica AI Security & Safety
Why this month's Microsoft patch release is a doozy
TechCrunch AI Security & Safety
Hackers are stealing Claude tokens from subscribers
Ars Technica AI Security & Safety
“This is the AI men actually use”: Meta ads pushed apps nudifying real teens
TechCrunch AI Security & Safety
Chrome is now shipping updates every 2 weeks as AI changes the security landscape
Bloomberg Technology Security & Safety
Meta Ran Hundreds of Ads Showing AI Child Sexual Abuse, NGO Says
Bloomberg Technology Security & Safety
Boston Scientific Warns of Financial Hit from Cyber Attack
Mashable Security & Safety
OpenAI is figuring out how to tell people when its agents go rogue
arXiv cs.AI Security & Safety
Rethinking Indirect Prompt Injection as a Test-Time Search Problem
arXiv cs.AI Security & Safety
The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation…
arXiv cs.AI Security & Safety
CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls
arXiv cs.AI Security & Safety
Uncensored Open-weight Models: Redistribution as the Persistence Layer
arXiv cs.AI Security & Safety
Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection
arXiv cs.AI Security & Safety
AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks
arXiv cs.AI Security & Safety
When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalize…
Engadget Security & Safety
OpenAI responds after report exposed another incident in which its AI agents went rogue
Mashable Security & Safety
Rogue AI agents commandeered German website and used it as a messaging board
The Verge AI Security & Safety
OpenAI admits to German wiki ‘incident’
Wired AI Security & Safety
OpenAI Agents Hacked Another Website
Latent Space (swyx) Security & Safety
[AINews] Collusion.wiki: A second undisclosed OpenAI agent swarm incident...