Prompt injection used to be a problem about a single input. Defenders inspected a string, or an image, or an audio clip, and asked whether that single channel carried a malicious instruction. Multimodal models break that assumption.
Published work
AI security contributions
The growing demand for accelerated computing is driving widespread deployment of multi-accelerator systems in the cloud and at the edge.
Large Language Models (LLMs) have enabled the development of powerful agentic systems capable of automating complex workflows across various fields.
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
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.
Privacy protection has become an increasing concern in modern machine learning applications.
Private information retrieval (PIR) allows private database queries; however, it is hindered by intense server-side computation and memory traffic.
Multi-user virtual reality enables immersive interaction. However, rendering avatars for numerous participants on each headset incurs prohibitive computational overhead, limiting scalability.
Approximate nearest neighbor (ANN) search in AI systems increasingly handles sensitive data on third-party infrastructure.
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.
Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or what it should convey.
Function secret sharing (FSS) is a core building block for privacy-preserving systems such as secure inference and private information retrieval (PIR), but incurs significant overhead in key generation, communication, and data
“We’re at an inflection point in cybersecurity,” Jensen Huang told a sold-out crowd at CrowdStrike’s Fal.Con 2026 in Las Vegas Tuesday. Attacks are now automated.
AI is changing the pace of cybersecurity. Agentic systems can coordinate work and pursue complex objectives over long horizons.
A frontier language model is only one component of an AI agent. The surrounding agent system—often called a harness—determines how the model receives context, uses tools, maintains state, responds to feedback, recovers from failure, and sustains progress over long-running tasks.
As AI agents become more capable and operate over longer horizons, building security and trust into the applications they power becomes increasingly important.
Surging AI demands are driving the need for massive datasets and context windows that burst past the confines of system memory. But rising needs aren’t met by simply adding more storage capacity.
Knowledge workers are increasingly integrating AI agents into their workflows. Agents that function as “digital coworkers” offer clear benefits.
Open source software is a critical pillar of the global economy. It underpins cloud computing, financial services, manufacturing, telecommunications, government and internet services by making technology accessible and observable to communities of experts.
Building a great AI agent isn’t just about choosing the right models. The harness is the architecture surrounding the model.
For over fifteen years, x86 CPUs have shipped with a dedicated hardware instruction for carryless multiplication. It’s a small but stubborn primitive that sits underneath authenticated encryption, error-correcting codes, and modern zero-knowledge proofs.
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.
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.
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.
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.