Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
DeFiFlowBench: Benchmarking and Improving Safe Executability in Natural-Language DeFi Workflow Synthesis
Abhinav Rajeev Kumar, Harshit Arora, Varun Singh +1
A structurally valid DeFi workflow can still authorize a costly trade. We introduce DeFiFlowBench, a benchmark of 207 team-authored prompts for natural-language DeFi workflow synth…
cs.LG2025
OverThink: Slowdown Attacks on Reasoning LLMs
Abhinav Kumar, Jaechul Roh, Ali Naseh +4
A reasoning language model (RLM) generates costly reasoning tokens, often hidden from the users, that help it excel at many tasks. Our Overthink attack targets RLM-based applicatio…