Hongxu Su

Hongxu Su, Mingzhe Liu, Jie Xu et al.

ERC-4337, the Ethereum account abstraction standard, simplifies account management and transaction fee payment in decentralized applications by introducing programmable smart contract wallets and gas sponsorship via paymasters. However, its heavy reliance on on-chain validation and frequent state updates incurs substantial gas overhead, leading to performance bottlenecks and limiting scalability in large-scale deployments. To mitigate these issues, we propose GasLiteAA, a framework that optimize ERC-4337 by offloading paymaster logic to Trusted Execution Environments (TEE). GasLiteAA delegates the secure execution of stateful gas sponsorship logic and user quota management to TEE, enforcing validation rules off-chain while anchoring their integrity on-chain via lightweight cryptographic attestations. This verifiable offloading architecture significantly reduces on-chain computation and storage costs without sacrificing verifiability or decentralization. Experimental results demonstrate that GasLiteAA substantially lowers transaction fees, while remaining fully compatible with Ethereum Layer 1. By balancing security, efficiency, and deployability, GasLiteAA provides a practical and scalable approach to gas sponsorship for account-abstraction-based decentralized applications.

Jianzhu Yao, Hongxu Su, Taobo Liao et al.

Neural networks increasingly run on hardware outside the user's control (cloud GPUs, inference marketplaces). Yet ML-as-a-Service reveals little about what actually ran or whether returned outputs faithfully reflect the intended inputs. Users lack recourse against service downgrades (model swaps, quantization, graph rewrites, or discrepancies like altered ad embeddings). Verifying outputs is hard because floating-point(FP) execution on heterogeneous accelerators is inherently nondeterministic. Existing approaches are either impractical for real FP neural networks or reintroduce vendor trust. We present NAO: a Nondeterministic tolerance Aware Optimistic verification protocol that accepts outputs within principled operator-level acceptance regions rather than requiring bitwise equality. NAO combines two error models: (i) sound per-operator IEEE-754 worst-case bounds and (ii) tight empirical percentile profiles calibrated across hardware. Discrepancies trigger a Merkle-anchored, threshold-guided dispute game that recursively partitions the computation graph until one operator remains, where adjudication reduces to a lightweight theoretical-bound check or a small honest-majority vote against empirical thresholds. Unchallenged results finalize after a challenge window, without requiring trusted hardware or deterministic kernels. We implement NAO as a PyTorch-compatible runtime and a contract layer currently deployed on Ethereum Holesky testnet. The runtime instruments graphs, computes per-operator bounds, and runs unmodified vendor kernels in FP32 with negligible overhead (0.3% on Qwen3-8B). Across CNNs, Transformers and diffusion models on A100, H100, RTX6000, RTX4090, empirical thresholds are $10^2-10^3$ times tighter than theoretical bounds, and bound-aware adversarial attacks achieve 0% success. NAO reconciles scalability with verifiability for real-world heterogeneous ML compute.