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
The Safeguard Worked. Is the LLM System Safer?
arXiv cs.AI Security & Safety
Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderati…
Mashable Security & Safety
OpenAI confirms Astra has reached critical cyber threshold, but will be available soon
NVIDIA Blog Security & Safety
NVIDIA and CrowdStrike Strengthen Agentic Cybersecurity Frontier
TechCrunch AI Security & Safety
Open AI’s Astra model is on the way—and very good at breaking into computer systems
Bloomberg Technology Security & Safety
Dropbox User Accounts Breached by Hackers Who Accessed Data
The Verge AI Security & Safety
OpenAI delayed its new model’s development after the Hugging Face hack
Bloomberg Technology Security & Safety
Palo Alto Networks Tops Profit Outlook on AI Security Demand
Bloomberg Technology Security & Safety
OpenAI Will Limit Access to New Astra Model’s Cybersecurity Features
AI News Security & Safety
Why MCP servers are becoming AI’s newest attack surface
arXiv cs.AI Security & Safety
Will the User Ever Know? Covert Indirect Prompt Injection Attacks on Tool-Using LLM Agents
arXiv cs.AI Security & Safety
Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
arXiv cs.AI Security & Safety
Robustness of Vision Language Models Against Split-Image Harmful Input Attacks
arXiv cs.AI Security & Safety
EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolvin…
arXiv cs.AI Security & Safety
Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agen…
arXiv cs.AI Security & Safety
AgenTRIM: Tool Risk Mitigation for Agentic AI
TechCrunch AI Security & Safety
Apple shares ‘shocking evidence’ against former employee accused of stealing company data…
MIT Technology Review AI Security & Safety
Hugging Face hack could indicate cultural issues at OpenAI
Bloomberg Technology Security & Safety
Polish Intelligence Probes Fire at Top Drone Firm WB Electronics
arXiv cs.AI Security & Safety
FISGuard: Defending Against Membership Inference via Fixed Input Subspaces
arXiv cs.AI Security & Safety
ContextLeak: Exfiltrating LLM Agent Context via Malicious Tools
arXiv cs.AI Security & Safety
The Instability of Safety: How Random Seeds and Temperature Expose Inconsistent LLM Refus…
arXiv cs.AI Security & Safety
OpenStamp: A Watermark for Open-Source Language Models
arXiv cs.AI Security & Safety
Quantization-Triggered Backdoors in Language Models: Cross-Quantizer Transferability and …
arXiv cs.AI Security & Safety
When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI
Bloomberg Technology Security & Safety
Author Explores Cybersecurity Risks of Driverless Cars
Hacker News (AI filter) Security & Safety
Smartphone LED detects hidden cameras with AI
Wired AI Security & Safety
The Cybersecurity Apocalypse Is Coming in ‘Months,’ AI Giants Warn
Bloomberg Technology Security & Safety
SentinelOne CEO on Earnings, AI's Cybersecurity Impact
Wired AI Security & Safety
He Scraped All of Their Art for AI. Now He’s Collaborating on a Tool to Help Them