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
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
arXiv cs.AI Security & Safety
CVE-TTP KG: Knowledge Graph Linking Software Vulnerabilities to Attack Behaviors
AWS Machine Learning Blog Security & Safety
Safely Releasing Frontier Models to Customers
Ars Technica AI Security & Safety
New attack provides one more reason why AI browsers are a bad idea
Bloomberg Technology Security & Safety
TikTok Finalizing Settlement of Addiction Lawsuit to Avoid Trial
Microsoft Source (AI + Cloud) Security & Safety
Securing AI agents: When AI tools move from reading to acting
Bloomberg Technology Security & Safety
AI Notetakers in Meetings Raise Mounting Privacy Concerns
Mashable Security & Safety
A clip of Erling Haaland eating has gone viral. Its not real.
Bloomberg Technology Security & Safety
What the Saga Over Anthropic’s Mythos Tells Us About the Cyber Risks From AI
Wired AI Security & Safety
Meta Contractors Posed as Teens to Prompt Rival Chatbots About Suicide, Sex, and Drugs
Hugging Face Daily Papers Security & Safety
Wireless Backdoor Attack and Defense for Semantic Communications over Multiple Access Cha…
Hugging Face Daily Papers Security & Safety
A Hybrid Framework For Crypto-Ransomware Detection In Enterprise Shared Storage
Hugging Face Daily Papers Security & Safety
Defending Against Harmful Supervision Hidden in Benign Samples
AI News Security & Safety
Best Automated Security Testing Tools for Modern DevSecOps
arXiv cs.AI Security & Safety
MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
arXiv cs.AI Security & Safety
Agent-Native Immune System: Architecture, Taxonomy, and Engineering
arXiv cs.AI Security & Safety
Room for Error: Large-Scale Simulation of Over-the-Air Acoustic Attacks
arXiv cs.AI Security & Safety
Seven Security Challenges That Must be Solved in Cross-domain Multi-agent LLM Systems
arXiv cs.AI Security & Safety
PRISON: Unmasking the Criminal Potential of Large Language Models
arXiv cs.AI Security & Safety
On the Inseparability of Instructions and Data in Shared-Embedding Sequence Models
arXiv cs.AI Security & Safety
Agentic AI-Powered Re-Identification: An Emerging, Scalable Threat to Mobility Microdata …
arXiv cs.AI Security & Safety
Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head…
arXiv cs.AI Security & Safety
Govern the Repository, Not the Agent: Measuring Ecosystem-Level Risk in AI-Native Software
arXiv cs.AI Security & Safety
Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs
Bloomberg Technology Security & Safety
Chinese Spies, Smuggled Drugs Fuel Takaichi’s Security Push
Hugging Face Daily Papers Security & Safety
Bit-ViP: Leveraging Bit-planes to Preserve Visual Privacy in Images through Obfuscation
arXiv cs.AI Security & Safety
ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP
arXiv cs.AI Security & Safety
From Celebrities to Anyone: Characterizing AI Nudification Content, Technology, and Commu…
arXiv cs.AI Security & Safety
Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities In…
arXiv cs.AI Security & Safety
HauntAttack: When Attack Follows Reasoning as a Shadow