# Better Security.  Less complexity.

Deploy any Docker container into a Trusted Execution Environment with zero code changes. Hardware-level isolation keeps your data private from cloud providers and admins.

## Hardware Memory Encryption

- Intel TDX + NVIDIA Support
- Cryptographic Attestation
- Real-time Verification
- Zero Code Changes
- Hardware Support

## Multi-TEE platform for every confidential computing use case you can think of.

From CPU-intensive workloads to GPU-accelerated AI, we support all major Trusted Execution Environment technologies.

### Performance

95% native performance with full security guarantees. 2-5% CPU overhead, 5-7% GPU overhead while maintaining hardware acceleration.

## Intel TDX Architecture

Trust Domain Extensions for x86 with CPU-generated keys and TDX Report attestation. Best for web services and traditional ML.

[Learn more](https://www.intel.com/content/www/us/en/products/docs/accelerator-engines/trust-domain-extensions.html)

## AMD SEV

Secure Encrypted Virtualization technology providing VM-level isolation with encrypted memory for diverse workloads.

[Learn more](https://www.amd.com/en/developer/sev.html)

## NVIDIA Confidential Computing

H100/H200 GPU TEE for AI workloads with 80GB+ secure memory and hardware memory encryption on GPU.

[Learn more](https://docs.phala.com/phala-cloud/confidential-ai/overview#confidential-gpu)

## Multi-Hardware Support

Deploy across Intel Xeon 4th gen (Sapphire Rapids), NVIDIA H100/H200, and AMD EPYC processors from a single unified platform.

## ARM TrustZone Coming soon

Mobile and edge computing support with ARM Confidential Compute Architecture for IoT and edge deployments.

## Phala Cloud Worldwide Network

Our distributed infrastructure spans multiple continents, providing low-latency access to confidential computing resources globally.

| Total vCPUs | Total H200 GPUs | Global Locations |
|--------------|-----------------|------------------|
| 1848         | 24              | 6                |

### Nodes (12)

| Location     | Node Name | Type | Configuration  |
|--------------|-----------|------|----------------|
| 🇮🇳         | gpu-in2   | GPU  | Intel Xeon Platinum 8580 • 240 cores • H200 x8 |
| 🇮🇳         | gpu-in1   | GPU  | Intel Xeon Platinum 8580 • 240 cores • H200 x8 |
| 🇺🇸         | gpu-08    | GPU  | Intel Xeon Platinum 8558 • 192 cores • H200 x8 |
| 🇺🇸         | prod5     | CPU  | Intel Xeon 6710E • 128 cores |
| 🇬🇧         | prod6     | CPU  | Intel Xeon Gold 6554S • 144 cores |
| 🇺🇸         | prod7     | CPU  | Intel Xeon 6710E • 128 cores |
| 🇺🇸         | prod9     | CPU  | Intel Xeon 6710E • 128 cores |
| 🇫🇷         | prod10    | CPU  | Intel Xeon Gold 5515+ • 32 cores |
| 🇺🇸         | prod8     | CPU  | Intel Xeon 6780E • 288 cores |
| 🇺🇸         | prod2     | CPU  | Intel Xeon Gold 5512U • 56 cores |
| 🇺🇸         | prod4     | CPU  | Intel Xeon Gold 6530 • 128 cores |
| 🇺🇸         | prod1     | CPU  | Intel Xeon Gold 6554S • 144 cores |

## Deploy confidential containers with cryptographic verification

### Container Preparation

Use your existing Docker workflow - no code changes needed. Build, tag, and deploy containers exactly as you do today.

[Learn more](https://docs.phala.com/phala-cloud/cvm/create-with-docker-compose)

```bash
# Build your Docker image
docker build -t myapp:latest .

# Create docker-compose.yml
cat > docker-compose.yml <<EOF
version: '3'
services:
  app:
    image: myapp:latest
    ports:
      - "3000:3000"
    environment:
      - DATABASE_URL=${DATABASE_URL}
      - API_KEY=${API_KEY}
EOF

# Deploy to Phala CVM
npx phala cvms create -n myapp \
  --compose docker-compose.yml
```

## Zero-trust confidential computing

Hardware-backed security guarantees with enterprise-grade performance.

### Memory Encryption

Hardware-level encryption of all memory pages with CPU/GPU generated keys.

### Native Performance

5% overhead while maintaining full security guarantees and hardware acceleration.

### Attack Resistance

Protection against privileged access, cold boot, and side-channel attacks.

### Zero Migration

Deploy existing Docker containers without code changes or special libraries.

### Live Attestation

Real-time cryptographic proof of integrity with public verification endpoints.

### Multi-Hardware

Support for Intel TDX, NVIDIA GPU TEE, and AMD SEV from one platform.

## Seamlessly integrates with your developer tools

Deploy confidential containers using your existing development stack. No need to learn new tools or change your workflow.

[Learn about Zero-Trust Framework](https://docs.phala.com/dstack/design-documents/decentralized-root-of-trust)

## FAQ

### Common Questions & Answers

1. **What's the difference between Intel TDX and NVIDIA GPU TEE?**  
Intel TDX provides VM-level CPU isolation while NVIDIA GPU TEE offers hardware-secured GPU memory and compute for AI workloads.

2. **Do I need to modify my Docker containers for TEE deployment?**  
No modifications needed. Your existing containers work as-is with automatic TEE security applied at infrastructure level.

3. **How do I verify my application is running in genuine TEE?**  
Use attestation endpoints to get cryptographic reports signed by Intel/NVIDIA hardware proving TEE genuineness and code integrity.

4. **What's the performance impact of memory encryption?**  
CPU workloads see 2-5% overhead, GPU AI/ML workloads see 5-7% overhead while maintaining hardware acceleration.

5. **Can Phala operators access my running containers?**  
No. TEE hardware prevents any external access including from operators, cloud providers, or system administrators.

6. **How does environment variable encryption work?**  
Variables are encrypted with TEE public keys during deployment. Only your running TEE instance can decrypt them.

7. **What compliance standards does this meet?**  
SOC 2 Type I certified and HIPAA compliant, with ISO 27001 in progress. Supports GDPR and FedRAMP requirements with hardware-backed security guarantees and audit trails.

8. **How do I debug applications running in TEE?**  
Standard debugging tools work through encrypted channels. Remote debugging, logging, and profiling maintain security.