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
DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
arXiv cs.AI Security & Safety
SoK: Rethinking Jailbreaking in the Era of Agentic AI: Attacks, Defenses, and Practical C…
arXiv cs.AI Security & Safety
AI Safety: Not Optional, Not Later
arXiv cs.AI Security & Safety
Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks
arXiv cs.AI Security & Safety
Membership Inference Attacks on Recommender System: A Survey
arXiv cs.AI Security & Safety
A Graph-Based Approach for Mapping Kernel-Level Telemetry to MITRE ATT&CK
Bloomberg Technology Security & Safety
Rogue AI Breakouts Raise Pressure for New Rules
The Verge AI Security & Safety
OpenAI’s rogue AI tried to hack another company in May
Engadget Security & Safety
OpenAI agents hacked a software service before the Hugging Face incident
Hacker News (AI filter) Security & Safety
The Worst Spam Emails: Inside iLands' AI Agent Hustle
Wired AI Security & Safety
From Hacks to Bioweapons, Claude Misuse Is Now Everywhere
arXiv cs.AI Security & Safety
No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vu…
arXiv cs.AI Security & Safety
DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injectio…
arXiv cs.AI Security & Safety
Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against …
arXiv cs.AI Security & Safety
Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Thre…
arXiv cs.AI Security & Safety
Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitiv…
arXiv cs.AI Security & Safety
A Survey of Threats Against Voice Authentication and Anti-Spoofing Systems
arXiv cs.AI Security & Safety
Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks
arXiv cs.AI Security & Safety
Temporal and Multimodal Deep Learning for Cyberattack Detection in LEO Satellite Systems
TechCrunch AI Security & Safety
An Anthropic researcher’s doomsday warning comes at a very interesting time
The Verge AI Security & Safety
Anthropic spent this week in hot water over cybersecurity
Ars Technica AI Security & Safety
Claude users found ways around safeguards for bioweapons research
Bloomberg Technology Security & Safety
Anthropic Says US Adversaries Aimed Claude at Weapons Research
Bloomberg Technology Security & Safety
Anthropic Says Yemeni Cell Used Claude in Missile Development
Engadget Security & Safety
Anthropic caught scientists using Claude to further biological weapon research
TechCrunch AI Security & Safety
Anthropic details distillation campaigns from Alibaba, Moonshot AI, and DeepSeek
Bloomberg Technology Security & Safety
Former OpenAI, Anthropic Employee Post, Hugging Face Hack Sound Alarm on AI
Mashable Security & Safety
Avian flu, drone swarms, and mass surveillance included in Anthropics safety report
Bloomberg Technology Security & Safety
Moonshot Secretly Routed User Requests Through Claude, Anthropic Says
TechCrunch AI Security & Safety
AI agents are flooding public services with new requests