Duanyi Yao (Navalabs), Siddhartha Jagannath (Navalabs), Baltasar Aroso (Navalabs), Vyas Krishnan (Navalabs), Ding Zhao (Navalabs)

Intent-based DeFi systems enable users to specify financial goals in natural language while automated solvers construct executable transactions. However, misalignment between a user’s stated intent and the resulting on-chain transaction can cause direct financial loss. A solver may generate a technically valid transaction that silently violates semantic constraints. Existing validation approaches fail to address this gap. Rule-based validators reliably enforce protocol-level invariants such as token addresses and numerical bounds but cannot reason about semantic intent, while LLM-based validators understand natural language yet hallucinate technical facts and mishandle numeric precision.

We introduce Arbiter, a hybrid Graph-of-Thoughts validation framework that decomposes intent–transaction alignment into a directed acyclic graph composing deterministic rule-based checks with LLM-based semantic reasoning. The graph progresses from concrete validation (token, amount, structural checks) to holistic analysis (intent consistency, adversarial detection), enabling early termination on critical failures, parallel execution where dependencies allow, and auditable node-level justifications.

To ground evaluation, we release INTENT-TX-18K, the first large-scale benchmark for this problem, built from real CoW Protocol, Uniswap, and Compound transactions with annotations for decision labels, violation families, and failure localization across aligned cases and four violation types. The dataset is available at https://github.com/duanyiyao/intent-tx-18k . Arbiter surpasses rule-only and LLM-only baselines in decision accuracy and F1 score, reduces hallucination-driven errors through deterministic grounding, improves failure localization, and maintains practical latency for production deployment.

View More Papers

PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning

Chen GONG (University of Virginia), Zheng Liu (University of Virginia), Kecen Li (University of Virginia), Tianhao Wang (University of Virginia)

Read More

FLIPPYRAM: A Large-Scale Study of Rowhammer Prevalence

Martin Heckel (Hof University of Applied Sciences), Nima Sayadi (Hof University of Applied Sciences), Jonas Juffinger (Graz University of Technology), Carina Fiedler (Graz University of Technology), Daniel Gruss (Graz University of Technology), Florian Adamsky (Hof University of Applied Sciences)

Read More

Robust Fraud Transaction Detection: A Two-Player Game Approach

Qi Tan (College of Computer Science and Software Engineering, Shenzhen University), Yi Zhao (School of Cyberspace Science and Technology, Beijing Institute of Technology), Laizhong Cui (College of Computer Science and Software Engineering, Shenzhen University), Qi Li (Institute for Network Science and Cyberspace, Tsinghua University), Ming Zhu (Department of Computer Science and Technology, Tsinghua University), Xing…

Read More