Explorar

Noticias de IA

1057 elementos — filtrados, clasificados y sin duplicados

Engadget Security & Safety
AI is changing cybersecurity in quick and terrifying ways
OpenAI News Security & Safety
Responding to the next frontier of critical cyber capabilities
Ars Technica AI Security & Safety
AI chatbots have failed people in crisis. Can that be fixed?
Engadget Security & Safety
Are Ray-Ban Meta glasses a privacy risk? Here's what you should know
Engadget Security & Safety
Chinese AI model Moonshot Kimi K3 also escaped its testing environment
Bloomberg Technology Security & Safety
China’s Top AI Model Evaded Testing Environment, Researchers Say
AINews / smol.ai Security & Safety
not much happened today
arXiv cs.AI Security & Safety
One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs
arXiv cs.AI Security & Safety
Hijacking Robots with a Piece of Paper: A Systematic Study of Physical Prompt Injection i…
arXiv cs.AI Security & Safety
When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Sy…
Wired AI Security & Safety
One of China’s Most Powerful AI Models Has Also Escaped Containment
Engadget Security & Safety
AI is now making new viruses
Mashable Security & Safety
Meta: One of our models escaped containment and hacked someone too!
Engadget Security & Safety
Meta claims its own AI also hacked into a third-party service during testing
Hacker News (AI filter) Security & Safety
Humans missed 1 in 3 threats approving AI agent commands across 40k game runs
Engadget Security & Safety
OpenAI's agents reportedly shared exploits with each other through a messaging board
Engadget Security & Safety
Apple's Private Relay feature could reveal your IP address to websites and services
arXiv cs.AI Security & Safety
Dynamic Jailbreaking Attack
arXiv cs.AI Security & Safety
AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection
arXiv cs.AI Security & Safety
Breadcrumbing Search Agents
arXiv cs.AI Security & Safety
Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning
Bloomberg Technology Security & Safety
OpenAI Models Joined Forces Months Ahead of Hugging Face Hack
Wired AI Security & Safety
OpenAI Didn’t Notice Its AI Agents Using a Message Board to Plan Their Hacking Spree
Wired AI Security & Safety
OpenAI’s Browser Could Be Hijacked to Spam Your WhatsApp Contacts
Bloomberg Technology Security & Safety
Meta AI Model Accessed Internet, Hacked Outside Firm in Testing
Ars Technica AI Security & Safety
Anthropic’s AI used fake identities, malware in rogue attack on GitHub project
Wired AI Security & Safety
The Most Dangerous AI Hacking Techniques Still Have Humans in the Loop
Engadget Security & Safety
Meta apps displayed ads that contained AI-generated CSAM
Wired AI Security & Safety
AI Worms and Viruses Are Coming
Microsoft Source (AI + Cloud) Security & Safety
Advance Zero Trust for AI: New tools and guidance to secure AI agents and DevSecOps