Español

Explorar

Noticias de IA

1057 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
The Unseen Hand: Manipulating Model Fairness and SHAP with Targeted Identity Re-Associati…
arXiv cs.AI Security & Safety
From CVE to CWE: Syscall-Based HIDS Generalisation
arXiv cs.AI Security & Safety
LambdaMark: Semantic Audio Watermarking for Robustness and Radioactivity
arXiv cs.AI Security & Safety
Local LLM Agents as Vulnerable Runtimes:A Source-Code Audit of the Agent Runtime Layer
arXiv cs.AI Security & Safety
Whose Agent Are You? Multi-Layer Fingerprinting and Attribution of Autonomous Web Agents
arXiv cs.AI Security & Safety
Signals in the Noise: Open Source Intelligence (OSINT) for AI Loss of Control Detection
arXiv cs.AI Security & Safety
AgentRiskBOM: A Risk-Scoping Security Bill of Materials for Agentic AI Systems
TechCrunch AI Security & Safety
OpenAI launches new initiative to help find and patch open-source bugs
Latent Space (swyx) Security & Safety
Red-Teaming after Mythos — Zico Kolter & Matt Fredrikson, Gray Swan
Wired AI Security & Safety
Meta Exposed Data Internally From Its Controversial Employee-Tracking Program
Engadget Security & Safety
Tesla in autopilot crashed into Texas home, killing one
Hugging Face Daily Papers Security & Safety
TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger
Hugging Face Daily Papers Security & Safety
The Watermark Shortcut: How Provenance Marking Sabotages Audio Deepfake Detection
The Verge AI Security & Safety
Read this before you vibe-code another app
Wired AI Security & Safety
World Cup Scams Are Getting Harder to Spot
Hugging Face Daily Papers Security & Safety
Intent-Governed Tool Authorization for AI Agents
Hugging Face Daily Papers Security & Safety
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
Hugging Face Daily Papers Security & Safety
From CVE to CWE: Syscall-Based HIDS Generalisation
Hugging Face Daily Papers Security & Safety
Detecting and Understanding Vulnerabilities in Fully Homomorphic Encryption Frameworks
AI News Security & Safety
e2e-assure introduces Cumulo, the U.K.’s only sovereign, AI-driven, zero-day SOC platform…
arXiv cs.AI Security & Safety
Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Sys…
arXiv cs.AI Security & Safety
Multi-View Decompilation for LLM-Based Malware Classification
arXiv cs.AI Security & Safety
LLM agent safety, multi-turn red-teaming, jailbreak benchmarks, adversarial robustness, s…
Microsoft Source (AI + Cloud) Security & Safety
Beyond the benchmark: Advancing security at AI speed
Hacker News (AI filter) Security & Safety
The hacker sent by Anthropic to calm the government's nerves about AI safety
Microsoft Source (AI + Cloud) Security & Safety
AI is accelerating cyberattacks — here’s how to stay ahead
Ars Technica AI Security & Safety
"Dangerous" AI models are coming no matter what
Hugging Face Daily Papers Security & Safety
Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution
arXiv cs.AI Security & Safety
Graph neural networks at war: integrating cybersecurity and drone intelligence in the Isr…
arXiv cs.AI Security & Safety
Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents