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
Security and Privacy in Agentic AI: Grand Challenges and Future Directions
arXiv cs.AI Security & Safety
When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents
arXiv cs.AI Security & Safety
From Beats to Breaches:How Offensive AI Infers Sensitive User Information from Playlists
arXiv cs.AI Security & Safety
Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of …
Ars Technica AI Security & Safety
Suspecting AI cheating, Ivy League prof ordered an in-person final; scores fell 50%
TechCrunch AI Security & Safety
Google’s deepfake detector system used to debunk McConnell hoax pic
Ars Technica AI Security & Safety
Lawsuit: Man used Grok to make 7K sex images of stepdaughter, then shot himself
Mashable Security & Safety
Discord confirms AI moderators have banned thousands over harmless images
Ars Technica AI Security & Safety
Hackers can use 9 of the most popular AI tools to assemble massive botnets
Hacker News (AI filter) Security & Safety
GitLost: We Tricked GitHub's AI Agent into Leaking Private Repos
arXiv cs.AI Security & Safety
The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access …
arXiv cs.AI Security & Safety
Evaluating calibrated refusal and safe usefulness in dual-use biology settings
TechCrunch AI Security & Safety
Discord admits AI moderation bug wrongfully banned users over harmless images
Hacker News (AI filter) Security & Safety
AI Meets Cryptography 1: What AI Found in Cloudflare's Circl
Bloomberg Technology Security & Safety
ECB Asks Banks for Plans to Address AI Cybersecurity Threats
Mashable Security & Safety
Taylor Swifts wedding photos are going viral. Theres just one problem.
arXiv cs.AI Security & Safety
Securing Multi-Tool AI Agent Chains With Dynamic, Real-Time Compositional Policies
arXiv cs.AI Security & Safety
Measuring the Robustness of Audio Deepfake Detection under Real-World Corruption
arXiv cs.AI Security & Safety
Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI A…
arXiv cs.AI Security & Safety
Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Mo…
arXiv cs.AI Security & Safety
When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Age…
arXiv cs.AI Security & Safety
Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and D…
arXiv cs.AI Security & Safety
Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives
arXiv cs.AI Security & Safety
Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions
arXiv cs.AI Security & Safety
Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL
arXiv cs.AI Security & Safety
DualView: Preventing Indirect Prompt Injection in Personal AI Agents
arXiv cs.AI Security & Safety
Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Age…
arXiv cs.AI Security & Safety
Agent Data Injection Attacks are Realistic Threats to AI Agents
arXiv cs.AI Security & Safety
Agentic SABRE: An Uncertainty-Aware Neuro-Symbolic Multi-Agent Framework for Adaptive Ran…
TechCrunch AI Security & Safety
The ‘first’ AI-run ransomware attack still needed a human