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
Mashable Security & Safety
Are we on fire, dude? When a Waymo ran over a firework
Ars Technica AI Security & Safety
Secret Claude tracker shocks users after Anthropic’s anti-surveillance stance
Bloomberg Technology Security & Safety
AI Poses Biggest Security Challenge of Decade, UK’s Cooper Warns
Hacker News (AI filter) Security & Safety
A sociotechnical threat model for AI-driven smart home devices
Hugging Face Daily Papers Security & Safety
DualView: Preventing Indirect Prompt Injection in Personal AI Agents
Bloomberg Technology Security & Safety
Greek Politician Investigating Spyware Had Mobile Phone Hacked
arXiv cs.AI Security & Safety
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
arXiv cs.AI Security & Safety
DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement …
arXiv cs.AI Security & Safety
Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in L…
AWS Machine Learning Blog Security & Safety
How Amazon Bedrock catches AI-generated phishing
Engadget Security & Safety
Threads' ubiquitous Mr Beast spam is part of a massive crypto scam network
Hugging Face Daily Papers Security & Safety
Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbr…
Hugging Face Daily Papers Security & Safety
Beyond Gradient-Based Attacks: Adversarial Robustness and Explainability Stability in Cyb…
arXiv cs.AI Security & Safety
SoK: Attack and Defense Landscape of Mobile On-device AI Systems
arXiv cs.AI Security & Safety
Recovering Input Text from Hidden States: Study of Gradient-Based Inversion of Decoder-On…
arXiv cs.AI Security & Safety
Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces
arXiv cs.AI Security & Safety
Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique
Engadget Security & Safety
Apple's Hide My Email may not be hiding anything
Microsoft Source (AI + Cloud) Security & Safety
Accelerating the quantum-safe timeline
Wired AI Security & Safety
You Can Now Sound the Alarm on AI Behaving Badly
Hugging Face Daily Papers Security & Safety
Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Em…
Wired AI Security & Safety
Claude Helped a Hacker Find a Way to Issue Tickets to Almost Every US Music Festival
arXiv cs.AI Security & Safety
Detecting Audio Deepfakes on the Edge:Lightweight SSL-Based Detection in a Browser Plugin
arXiv cs.AI Security & Safety
Curvature-Guided Module Localization for Low-Rank Detoxification of Backdoored Large Lang…
arXiv cs.AI Security & Safety
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
arXiv cs.AI Security & Safety
Containment Verification: AI Safety Guarantees Independent of Alignment
arXiv cs.AI Security & Safety
An AI-Based Solution for Secure Service Provisioning in IoT
arXiv cs.AI Security & Safety
CVE-TTP KG: Knowledge Graph Linking Software Vulnerabilities to Attack Behaviors
arXiv cs.AI Security & Safety
Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense
arXiv cs.AI Security & Safety
AI-Generated PowerShell Malware: An Experimental Framework and Dataset