activity
20162023
most citedLearning to Detect Malicious Clients for Robust Federated Learning

187 citations · 641 across the 64 of their papers we have counts for

collaborators
Showing cs.CRShow all

12 papers · 1 filter

cs.CR2023

Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack

Hideaki Takahashi, Jingjing Liu, Yang Liu

Federated Learning with Model Distillation (FedMD) is a nascent collaborative learning paradigm, where only output logits of public datasets are transmitted as distilled knowledge,…

cs.CR20221 cited

Cargo Ecosystem Dependency-Vulnerability Knowledge Graph Construction and Vulnerability Propagation Study

Peiyang Jia, Chengwei Liu, Hongyu Sun +4

Currently, little is known about the structure of the Cargo ecosystem and the potential for vulnerability propagation. Many empirical studies generalize third-party dependency gove…

cs.CR202110 cited

Formal Analysis of Composable DeFi Protocols

Palina Tolmach, Yi Li, Shang-Wei Lin +1

Decentralized finance (DeFi) has become one of the most successful applications of blockchain and smart contracts. The DeFi ecosystem enables a wide range of crypto-financial activ…

cs.CR20204 cited

Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning

Jianwen Sun, Tianwei Zhang, Xiaofei Xie +4

Adversarial attacks against conventional Deep Learning (DL) systems and algorithms have been widely studied, and various defenses were proposed. However, the possibility and feasib…

cs.CR20206 cited

Advanced Evasion Attacks and Mitigations on Practical ML-Based Phishing Website Classifiers

Yusi Lei, Sen Chen, Lingling Fan +2

Machine learning (ML) based approaches have been the mainstream solution for anti-phishing detection. When they are deployed on the client-side, ML-based classifiers are vulnerable…

cs.CR2020

An Empirical Study on Benchmarks of Artificial Software Vulnerabilities

Sijia Geng, Yuekang Li, Yunlan Du +3

Recently, various techniques (e.g., fuzzing) have been developed for vulnerability detection. To evaluate those techniques, the community has been developing benchmarks of artifici…