Pinned
OPPO × Phala published a joint paper on Kubernetes Pod-level remote attestation for confidential AI.
Goal: prove the hardware, container image, and Pod identity before sensitive data enters the workload.
arxiv.org/abs/2606.03323
Phala
@PhalaNetwork
Empowering 10,000 builders and companies to build scalable, private, and safe intelligence.
- Kimi K3 is live on Phala for confidential frontier intelligence. 2.8T parameters. Native multimodality. 1M-token context. GPU TEE-backed inference for long-horizon coding and agent workflows. phala.com/models/moonsho…
- This incident is a strong case for evaluating frontier models inside confidential GPU environments. Hardware-enforced isolation and remote attestation can narrow what the workload can access and make the execution boundary verifiable as model capabilities rise.we had a significant security incident during evaluation of our models. we are sharing what we have learned so far. thanks to @huggingface for the partnership on this. openai.com/index/hugging-…
- #dstack private-ai-gateway can now route to custom @chutes_ai More confidential AI in the wild is good for private AI. Secure GPUs, TDX CPUs, and verifiable AI models are becoming table stakes.#dstack private-ai-gateway can now route to custom @chutes_ai deployments. The interesting part isn’t the routing. Before any prompt is forwarded, the gateway verifies the target GPU TEE against the expected measurements. And then it sends all the prompts via an e2e encryption.
- Great to see @iEx_ec laying out the trust foundation behind Nox—from Intel TDX and dstack boot-time attestation to secrets released only to known workloads. This is verifiable confidential compute becoming real infrastructure for onchain finance. Congrats to the iExec team 👏
