How Hugging Face Scaled Secrets Management for AI Infrastructure

Hugging Face Teams Up with Protect AI: Enhancing Model Security for the ML Community

CUGA on Hugging Face: Democratizing Configurable AI Agents

Scaling security with responsible disclosure

OpenAI introduces its Outbound Coordinated Disclosure Policy to guide how it responsibly reports vulnerabilities in third-party software—emphasizing integrity, collaboration, and proactive security at scale.

MOSAIC: Masked Outsourcing of Secure AI Computations

arXiv:2607. 29221v1 Announce Type: cross Abstract: We address the challenge of securely and efficiently outsourcing AI computations from a trusted but computationally weak client to an untrusted but powerful server, in the setting where the client holds both the input and the model, and the server must learn neither.

Hugging Face and JFrog partner to make AI Security more transparent

From data to decisions: how LSEG is scaling trusted AI

See how LSEG uses OpenAI to scale trusted AI across its global business, accelerating insights, shrinking release cycles, and empowering 4,000 employees.

When Agents Talk, Secrets Travel: Topology-Driven Leakage and Recipient-Conditioned Sanitization in Multi-Agent LLM Systems

arXiv:2610.16039v1 Announce Type: cross Abstract: Multi-agent LLM systems (MALS) introduce a privacy-leakage problem that conventional sensitivity-based defenses miss, since information disclosed to...

Hugging Face and VirusTotal collaborate to strengthen AI security

Traccia: An OpenTelemetry-Based Governance Platform for AI Systems

arXiv:2607. 14309v1 Announce Type: new Abstract: The rapid development of Large Language Models (LLMs) and Artificial Intelligent (AI) powered autonomous agents has fundamentally changed the existing forms of software governance.

AI Models Can Provably Hide Arbitrary Capabilities

The paper demonstrates that hidden capabilities in AI models can be provably concealed by embedding encrypted neural networks as backdoors within the host model’s weights. These hidden circuits are designed to decrypt and activate only when a secret trigger is provided, and they remain difficult to elicit or interpret even with full access to the model weights, thanks to cryptographic guarantees. The authors implement these constructions in PyTorch and test their resistance against various elicitation techniques on a chemical reaction prediction task, showing that current audit methods cannot reliably uncover such hidden behaviors.

Signal-based Model Access Risk Analysis for AI System Operations Security

arXiv:2607. 16414v1 Announce Type: cross Abstract: Artificial intelligence (AI) systems are now ubiquitous across domains such as security, finance, healthcare, consumer technology, and large-scale cloud services, where they process massive volumes of data and make consequential decisions daily.

Privacy-Preserving AI Verification via Minimal Information Disclosure

arXiv:2608. 02774v1 Announce Type: cross Abstract: AI verification crosses a trust boundary: a verifier must learn enough to establish an authorized claim, yet the same evidence can reveal sensitive details about the model, workload, or hardware.