2 citations · 3 across the 4 of their papers we have counts for
6 papers
Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning
Zihan Zhang, Shuangjie Yao, Zesen Liu +8
Semantic caches reduce LLM serving costs by reusing previously generated answers for semantically similar queries. However, retrieval is based solely on embedding similarity betwee…
EchoFuzz: Empowering Smart Contract Fuzzing with Large Language Models
Juanen Li, Peng Qian, Guanyan Li +6
Smart contracts, serving as the cornerstone of decentralized applications, autonomously manage trillion-dollar digital assets, making them attractive targets for attacks. Fuzzing h…
When Fuzzing Meets LLMs: Challenges and Opportunities
Yu Jiang, Jie Liang, Fuchen Ma +8
Fuzzing, a widely-used technique for bug detection, has seen advancements through Large Language Models (LLMs). Despite their potential, LLMs face specific challenges in fuzzing. I…
IntelliGen: Automatic Driver Synthesis for FuzzTesting
Mingrui Zhang, Jianzhong Liu, Fuchen Ma +2
Fuzzing is a technique widely used in vulnerability detection. The process usually involves writing effective fuzz driver programs, which, when done manually, can be extremely labo…
V-Gas: Generating High Gas Consumption Inputs to Avoid Out-of-Gas Vulnerability
Fuchen Ma, Ying Fu, Meng Ren +5
The out-of-gas error occurs when smart contract programs are provided with inputs that cause excessive gas consumption, and would be easily exploited to make the DoS attack. Multip…
EVMFuzz: Differential Fuzz Testing of Ethereum Virtual Machine
Ying Fu, Meng Ren, Fuchen Ma +3
Ethereum Virtual Machine (EVM) is the run-time environment for smart contracts and its vulnerabilities may lead to serious problems to the Ethereum ecology. With lots of techniques…