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
When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranki…
arXiv cs.AI Security & Safety
JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization
arXiv cs.AI Security & Safety
Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models
arXiv cs.AI Security & Safety
Goal-Autopilot: A Verifiable Anti-Fabrication Firewall for Unattended Long-Horizon Agents
arXiv cs.AI Security & Safety
Learning to Inject: Automated Prompt Injection via Reinforcement Learning
Bloomberg Technology Security & Safety
South Korea Fines Coupang Record $409 Million for Data Leak
Hacker News (AI filter) Security & Safety
AI agent runs amok in Fedora and elsewhere
Bloomberg Technology Security & Safety
OpenAI Says China-Linked Accounts Aim to Fuel US Data Center Pushback
TechCrunch AI Security & Safety
Cybersecurity researchers aren’t happy about the guardrails on Anthropic’s Fable
Bloomberg Technology Security & Safety
Anthropic CEO Doesn’t Know If Claude Used in Iran School Strike
Amazon Science Security & Safety
EC2’s formally verified “isolation engine” provides mathematical assura…
Wired AI Security & Safety
Wrongful Arrest Exposes Failures in One of the Oldest Police Face-Recognition Tools in th…
Hacker News (AI filter) Security & Safety
A €0.01 bank transfer could compromise a banking AI agent
OpenAI News Security & Safety
PRC-linked influence operations are targeting AI debates in the US
arXiv cs.AI Security & Safety
Dynamics of Adversarial Attacks on Large Language Model-Based Search Engines
arXiv cs.AI Security & Safety
Understanding and mitigating the risks of OpenClaw for non-technical users: A practical g…
arXiv cs.AI Security & Safety
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
arXiv cs.AI Security & Safety
BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
arXiv cs.AI Security & Safety
The Distributed Detectability Band Against Marginal-Preserving Attacks
arXiv cs.AI Security & Safety
GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines
arXiv cs.AI Security & Safety
Attacks on Machine-Text Detectors Retain Stylistic Fingerprints
arXiv cs.AI Security & Safety
A Source Domain is All You Need: Source-Only Cross-OS Transfer Learning for APT Anomaly D…
arXiv cs.AI Security & Safety
Assessing Automated Prompt Injection Attacks in Agentic Environments
arXiv cs.AI Security & Safety
Advancing the State-of-the-Art in Empirical Privacy Auditing
arXiv cs.AI Security & Safety
A Bayesian Network Approach for Enhancing Security-Focused Decision Support Systems
Hacker News (AI filter) Security & Safety
'Sloppenheimer:' Amazon Employees Mock the Company's AI on Slack
Engadget Security & Safety
The French government's internal messaging service was compromised in a security breach
Mashable Security & Safety
Conan OBrien, deepfake master, wants to stop you from getting pwned
AI News Security & Safety
Autonomous AI Data Loss in DevOps: Building Efficient Defenses
Hacker News (AI filter) Security & Safety
Microsoft's open source tools were hacked to steal passwords of AI developers