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
AINews / smol.ai Security & Safety
not much happened today
arXiv cs.AI Security & Safety
PlanFlip: Attacking Multi-Agent LLM Systems via Planning-Phase Prompt Injection
arXiv cs.AI Security & Safety
STAC: When Innocent Tools Form Dangerous Chains for LLM Agents
arXiv cs.AI Security & Safety
Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security
arXiv cs.AI Security & Safety
How Do You Choose Your AI Component? An Interview Study of Secure AI Integration in Pract…
arXiv cs.AI Security & Safety
Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech La…
arXiv cs.AI Security & Safety
Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video G…
Hugging Face Daily Papers Security & Safety
Broken Gates: Re-evaluating Web Bot Defenses in the Age of LLM Agents
Hugging Face Daily Papers Security & Safety
Hardware Mechanisms to Dynamically Throttle AI Performance
Hugging Face Daily Papers Security & Safety
An Early Warning of Emerging Biosecurity Risks in Frontier LLMs
Hugging Face Daily Papers Security & Safety
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
arXiv cs.AI Security & Safety
Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe L…
arXiv cs.AI Security & Safety
Poison to Detect: Detection of Targeted Overfitting in Federated Learning
arXiv cs.AI Security & Safety
FLINT: Fingerprinting Federated Learning Architectures from 5G PHY-Layer Side Channels
Wired AI Security & Safety
Your Period Tracker Is (Probably) Spying on You
Wired AI Security & Safety
Prompt Injection Attacks Are Thwarting AI Hacking Agents
TechCrunch AI Security & Safety
The Zoom hack that says, ‘Don’t record me’
Bloomberg Technology Security & Safety
IPhone Hacking Firm Sues Ex-Worker Over Alleged Theft of Secrets
Engadget Security & Safety
Zoox issues software recall because its robotaxis may be confused by smoke
Hacker News (AI filter) Security & Safety
AI Meets Cryptography 2: What AI Found in OpenVM's ZkVM
Engadget Security & Safety
Most smart appliances collect data: Here's how to find out what yours tracks
MIT Technology Review AI Security & Safety
The risk of weather data sabotage is rising
Ars Technica AI Security & Safety
xAI can’t deny Grok makes CSAM anymore. So it’s suing users.
VentureBeat AI Security & Safety
The agent security gap: 54% of enterprises have already had an AI agent incident, and mos…
Engadget Security & Safety
NTSB investigators confirm Tesla driver overrode Full Self-Driving system in fatal crash
Engadget Security & Safety
xAI sues Grok user for generating nonconsensual sexualized deepfakes
arXiv cs.AI Security & Safety
Adversarial Prompting Framework for AI Safety Assessment
arXiv cs.AI Security & Safety
Safeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assis…
arXiv cs.AI Security & Safety
Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavi…
arXiv cs.AI Security & Safety
PersGuard: Preventing Malicious Personalization in Text-to-Image Diffusion Models via Mod…