Published work

AI security contributions

Blog

Hardware-Rooted AI Security That Won’t Slow You Down

AI has transformed how organizations operate, driving unprecedented levels of productivity and innovation. However, AI adoption can be impeded by concerns surrounding data privacy, sovereignty and how to secure data while it is in use, or during inference and engagement with AI models.
Blog

NVIDIA Brings Trusted, 24/7 AI Agents to Telecom Operations

Telecom operators have seen remarkable returns from using generative AI to automate network management, customer care and back-office operations. Most of that impact has been task‑based: automation that speeds up predetermined steps while people manually correlate insights and direct next steps.
Blog

One-Click Multi-Tenant Security with  NVIDIA Quantum InfiniBand

NVIDIA Quantum InfiniBand now offers intent-based security profiles in Unified Fabric Manager (UFM) that enable multi-tenant fabric security in a single click. NVIDIA Quantum InfiniBand supports three profiles: General, Bare Metal Cloud, and Secured Bare Metal Cloud.
Research PaperJun 10, 2026

VIPIR: A Versatile GPU Framework for Integrating Private Information Retrieval Protocols

While private information retrieval (PIR) enables private database services by fully concealing access patterns, it simultaneously requires high computational throughput, large memory capacity, and substantial memory bandwidth.
Blog

NVIDIA Confidential Computing to Help Expand Apple’s Private Cloud Compute

NVIDIA GPUs with Confidential Computing are now used for confidential inference in Apple’s Private Cloud Compute (PCC), as it expands beyond Apple’s data centers to Google Cloud.
Blog

Advancing AI Infrastructure for Agentic AI with NVIDIA DOCA In-Silicon Security

The AI era is driving a new class of infrastructure: AI factories that transform data into intelligence for autonomous AI agents operating at unprecedented scale. Powered by accelerated computing, AI factories enable enterprises to train, fine-tune, and deploy AI with greater speed and efficiency.
Research PaperMay 30, 2026

GPUArmor: A Hardware-Software Co-design for Efficient and Scalable Memory Safety on GPUs

Memory safety errors continue to pose a significant threat to current computing systems, and graphics processing units (GPUs) are no exception. A prominent class of memory safety algorithms is allocation-based solutions.
Blog

How to Automate AI Model Documentation with the NVIDIA MCG Toolkit

As AI models grow in complexity and regulatory scrutiny intensifies under frameworks including California’s AB-2013 and the EU AI Act, software teams face a challenge beyond delivering great code: They need to produce comprehensive, auditable model document
Blog

NVIDIA-Verified Agent Skills Provide Capability Governance for AI Agents

Autonomous AI agents are becoming more capable. Open models, Model Context Protocol (MCP)-connected tools, and portable skills are also making agents easier to extend.But scaling agent use with structural transparency and operational integrity requires more than runtime guardrails.
Blog

Improving Bash Generation in Small Language Models with Grammar-Constrained Decoding

Bash is one of the most flexible and powerful interfaces exposed to AI agents. In the right system, a model that emits grep, curl, tar, or a shell pipeline is producing an executable action that can read files, mutate a workspace, open network connections, and chain tools together.
Blog

Mitigating Indirect AGENTS.md Injection Attacks in Agentic Environments

AI tools are significantly accelerating software development and changing how developers work with code. These tools serve as real-time copilots, automating repetitive tasks, executing tasks, writing documentation, and more.
Research PaperApr 19, 2026

Privatar: Scalable Privacy-preserving Multi-user VR via Secure Offloading

Multi-user virtual reality enables immersive interaction. However, rendering avatars for numerous participants on each headset incurs prohibitive computational overhead, limiting scalability.
Blog

Build a More Secure, Always-On Local AI Agent with OpenClaw and NVIDIA NemoClaw

Agents are evolving from question-and-answer systems into long-running autonomous assistants that read files, call APIs, and drive multi-step workflows. However, deploying an agent to execute code and use tools without proper isolation raises real risks—especially when using third-party cloud infrastructure due to data privacy and control.
Research PaperApr 6, 2026

GPIR: Enabling Practical Private Information Retrieval with GPUs

Private information retrieval (PIR) allows private database queries; however, it is hindered by intense server-side computation and memory traffic.
Research PaperMar 31, 2026

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions.
Research PaperMar 31, 2026

Beyond Latency: A System-Level Characterization of MPC and FHE for PPML

Privacy protection has become an increasing concern in modern machine learning applications.
Blog

How Autonomous AI Agents Become Secure by Design With NVIDIA OpenShell

Autonomous agents mark a new inflection point in AI. Systems are no longer limited to generating responses or reasoning through tasks.
Blog

Building a Zero-Trust Architecture for Confidential AI Factories

AI is moving from experimentation to production. However, most data enterprises need exists outside the public cloud.
Blog

Run Autonomous, Self-Evolving Agents More Safely with NVIDIA OpenShell

AI has evolved from assistants following your directions to agents that act independently. Called claws, these agents can take a goal, figure out how to achieve it, and execute indefinitely—while leaving you out of the loop.
Research PaperMar 15, 2026

Hunting CUDA Bugs at Scale with cuFuzz

GPUs play an increasingly important role in modern software. However, the heterogeneous host-device execution model and expanding software stack make GPU programs prone to memory-safety and concurrency bugs that evade static analyses.
Blog

NVIDIA Brings AI-Powered Cybersecurity to World’s Critical Infrastructure

As technologies and systems become more digitalized and connected across the world, operational technology (OT) environments and industrial control systems (ICS) — from energy and manufacturing to transportation and utilities — are increasingly depending on enterprise networks and the cloud. This expands OT and ICS capabilities — but also their exposure to cyber threats.
Blog

Practical Security Guidance for Sandboxing Agentic Workflows and Managing Execution Risk

AI coding agents enable developers to work faster by streamlining tasks and driving automated, test-driven development. However, they also introduce a significant, often overlooked, attack surface by running tools from the command line with the same permissions and entitlements as the user, making them computer use agents, with all the risks those entail.
Research PaperJan 29, 2026

ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models

Large reasoning models (LRMs) extend large language models with explicit multi-step reasoning traces, but this capability introduces a new class of prompt-induced inference-time denial-of-service (PI-DoS) attacks that exploit the high computational co
Blog

Updating Classifier Evasion for Vision Language Models

Advances in AI architectures have unlocked multimodal functionality, enabling transformer models to process multiple forms of data in the same context.
Research PaperJan 15, 2026

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack

Large Language Models (LLMs) have enabled the development of powerful agentic systems capable of automating complex workflows across various fields.