Explorar

Noticias de IA

1359 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Security & Safety
DiagChain: A Diagnostic Benchmark for Evaluating LLM Agents on Evidence-Grounded Attack C…
arXiv cs.AI Security & Safety
AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detecti…
arXiv cs.AI Security & Safety
Toward Understanding the Transferability of Adversarial Suffixes in Large Language Models
arXiv cs.AI Security & Safety
A Security-Oriented Lifecycle Model for Large Language Model Systems
arXiv cs.AI Security & Safety
Security-First Evaluation of Text-to-Terraform: Benchmarking LLMs and SLMs for Secure IaC…
Hugging Face Daily Papers Security & Safety
Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)
Wired AI Security & Safety
OK, Well, Rogue AI Agents Are Hacking Again
Hacker News (AI filter) Security & Safety
AI fuels more than half of cybercrime in Africa as scams surge – Interpol
Bloomberg Technology Security & Safety
OpenAI, Anthropic AI Models Involved in More Security Incidents
TechCrunch AI Security & Safety
Nvidia doesn’t mess around: A week after open AI industry group formed, it’s already show…
Bloomberg Technology Security & Safety
Data Centers Exposed US Telecoms to China Hacks, US Panel to Say
Bloomberg Technology Security & Safety
Hackers Steal Bitcoin, Visa Outlines Stablecoin Plans | Bloomberg Crypto 8/4/2026
OpenAI News Security & Safety
Third-party cyber evaluations involving OpenAI models
Engadget Security & Safety
Apple caps bug bounty program due to deluge of AI submissions
Bloomberg Technology Security & Safety
Apple Asks Judge to Bar OpenAI From Using Alleged Trade Secrets
Bloomberg Technology Security & Safety
AI Now Fuels Over Half of Africa’s Cybercrime, Study Finds
TechCrunch AI Security & Safety
Apple says more ex-employees may have taken confidential data to OpenAI
Hugging Face Daily Papers Security & Safety
ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization
arXiv cs.AI Security & Safety
VLAGuard: A Framework for Evaluating and Mitigating Physical Attention Hijacking in Visio…
arXiv cs.AI Security & Safety
Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs
arXiv cs.AI Security & Safety
When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems
arXiv cs.AI Security & Safety
Adversarial Attacks in Multi-Agent LLM Pipelines: Unveiling Structural Vulnerabilities in…
arXiv cs.AI Security & Safety
From Chasing Ghosts to Missed Attacks: Perspectives and Perceptions of SOC Practitioners …
arXiv cs.AI Security & Safety
Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Steal…
arXiv cs.AI Security & Safety
FL-OA: A Byzantine-Robust Federated Learning Framework with Outsourced Auditing for Intel…
arXiv cs.AI Security & Safety
Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks
arXiv cs.AI Security & Safety
Why Formal Monitors Fail: Attack Distribution Entropy as a Coverage Bound for LTL-Based L…
arXiv cs.AI Security & Safety
Exposed by Design: A Dynamic Security Assessment of Internet-Facing MCP Servers at Scale
arXiv cs.AI Security & Safety
No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks
arXiv cs.AI Security & Safety
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance