Published work

AI security contributions

Blog

Bring Receipts: New NVIDIA AI Blueprint Detects Fraudulent Credit Card Transactions With Precision

Financial losses from worldwide credit card transaction fraud are projected to reach more than $403 billion over the next decade.
Blog

Supercharging Fraud Detection in Financial Services with Graph Neural Networks (Updated)

Note: This blog post was originally published on Oct. 28, 2024, but has been edited to reflect new updates.
Blog

Stream Smarter and Safer: Learn how NVIDIA NeMo Guardrails Enhance LLM Output Streaming

​​LLM Streaming sends a model’s response incrementally in real time, token by token, as it’s being generated. The output streaming capability has evolved from a nice-to-have feature to an essential component of modern LLM applications.
Blog

Applying Autoencoder-Based GNNs for High-Throughput Network Anomaly Detection in NetFlow Data

As modern enterprise and cloud environments scale, the complexity and volume of network traffic increase dramatically. NetFlow is used to record metadata about the traffic flows traversing a network device such as a router, switch, or host.
Blog

Structuring Applications to Secure the KV Cache

When interacting with transformer-based models like large language models (LLMs) and vision-language models (VLMs), the structure of the input shapes the model’s output. But prompts are often more than a simple user query.
Blog

Advancing Cybersecurity Operations with Agentic AI Systems

The age of passive AI is over. A new era is beginning, where AI doesn’t just respond—it thinks, plans, and acts.
Blog

How Agentic AI Enables the Next Leap in Cybersecurity

Agentic AI is redefining the cybersecurity landscape — introducing new opportunities that demand rethinking how to secure AI while offering the keys to addressing those challenges. Unlike standard AI systems, AI agents can take autonomous actions — interacting with tools, environments, other agents and sensitive data.
Blog

NVIDIA Brings Cybersecurity to Every AI Factory

As enterprises increasingly adopt AI, securing AI factories — where complex, agentic workflows are executed — has never been more critical. NVIDIA is bringing runtime cybersecurity to every AI factory with a new NVIDIA DOCA software framework, part of the NVIDIA cybersecurity AI platform.
Blog

Announcing NVIDIA Secure AI General Availability

As many enterprises move to running AI training or inference on their data, the data and the code need to be protected, especially for large language models (LLMs). Many customers can’t risk placing their data in the cloud because of data sensitivity.
Blog

Effortless Federated Learning on Mobile with NVIDIA FLARE and Meta ExecuTorch

NVIDIA and the PyTorch team at Meta announced a groundbreaking collaboration that brings federated learning (FL) capabilities to mobile devices through the integration of NVIDIA FLARE and ExecuTorch.
Blog

Prevent LLM Hallucinations with the Cleanlab Trustworthy Language Model in NVIDIA NeMo Guardrails

As more enterprises integrate LLMs into their applications, they face a critical challenge: LLMs can generate plausible but incorrect responses, known as hallucinations. AI guardrails—or safeguarding mechanisms enforced in AI models and applications—are a popular technique to ensure the reliability of AI applications.
Blog

Measuring the Effectiveness and Performance of AI Guardrails in Generative AI Applications

Safeguarding AI agents and other conversational AI applications to ensure safe, on-brand and reliable behavior is essential for enterprises. NVIDIA NeMo Guardrails offers robust protection with AI guardrails for content safety, topic control, jailbreak detection, and more to evaluate and optimize guardrail performance.
Blog

CUDA Accelerated: How CUDA Libraries Bolster Cybersecurity With AI

Editor’s note: This is the next topic in our new CUDA Accelerated news series, which showcases the latest software libraries, NVIDIA NIM microservices and tools that help developers, software makers and enterprises use GPUs to accelerate their applications.
Blog

Defining LLM Red Teaming

There is an activity where people provide inputs to generative AI technologies, such as large language models (LLMs), to see if the outputs can be made to deviate from acceptable standards. This use of LLMs began in 2023 and has rapidly evolved to become a common industry practice and a cornerstone of trustworthy AI.
Blog

Agentic Autonomy Levels and Security

Agentic workflows are the next evolution in AI-powered tools.
Blog

Safety First: Leading Partners Adopt NVIDIA Cybersecurity AI to Safeguard Critical Infrastructure

The rapid evolution of generative AI has created countless opportunities for innovation across industry and research. As is often the case with state-of-the-art technology, this evolution has also shifted the landscape of cybersecurity threats, creating new security requirements.
Blog

NVIDIA Releases NIM Microservices to Safeguard Applications for Agentic AI

AI agents are poised to transform productivity for the world’s billion knowledge workers with “knowledge robots” that can accomplish a variety of tasks. To develop AI agents, enterprises need to address critical concerns like trust, safety, security and compliance.
Blog

How to Safeguard AI Agents for Customer Service with NVIDIA NeMo Guardrails

AI agents present a significant opportunity for businesses to scale and elevate customer service and support interactions. By automating routine inquiries and enhancing response times, these agents improve efficiency and customer satisfaction, helping organizations stay competitive.
Blog

NVIDIA Launches DRIVE AI Systems Inspection Lab, Achieves New Industry Safety Milestones

Editor’s note: This blog has been updated to reflect that NVIDIA DRIVE AI Systems Inspection Lab has been renamed to NVIDIA Halos AI Systems Inspection Lab. A new NVIDIA Halos AI Systems Inspection Lab will help automotive ecosystem partners navigate evolving industry standards for autonomous vehicle safety.
Blog

Sandboxing Agentic AI Workflows with WebAssembly

Agentic AI workflows often involve the execution of large language model (LLM)-generated code to perform tasks like creating data visualizations. However, this code should be sanitized and executed in a safe environment to mitigate risks from prompt injection and errors in the returned code.
Blog

Content Moderation and Safety Checks with NVIDIA NeMo Guardrails

Content moderation has become essential in retrieval-augmented generation (RAG) applications powered by generative AI, given the extensive volume of user-generated content and external data that these systems manage.
Blog

Automate Early Security Patching in CI Pipelines on AWS Using NVIDIA AI Blueprints

The evolution of modern application development has led to a significant shift toward microservice-based architectures. This approach offers great flexibility and scalability, but it also introduces new complexities, particularly in the realm of security.
Blog

Introducing NVIDIA cuPQC for GPU-Accelerated Post-Quantum Cryptography

In the past decade, quantum computers have progressed significantly and could one day be used to undermine current cybersecurity practices. If run on a quantum computer, for example, an algorithm discovered by the theoretical computer scientist Peter Shor could crack common encryption schemes, including the Rivest-Shamir-Adleman (RSA) encryption algorithm.
Blog

Exploring the Case of Super Protocol with Self-Sovereign AI and NVIDIA Confidential Computing

Confidential and self-sovereign AI is a new approach to AI development, training, and inference where the user’s data is decentralized, private, and controlled by the users themselves. This post explores how the capabilities of Confidential Computing (CC) are expanded through decentralization using blockchain technology.
Blog

Transforming Telecom Networks to Manage and Optimize AI Workloads

5G global connections numbered nearly 2 billion earlier this year, and are projected to reach 7.7 billion by 2028. While 5G has delivered faster speeds, higher capacity, and improved latency, particularly for video and data traffic, the initial promise of creating new revenues for network operators has remained elusive.