333 citations · 1.3k across the 71 of their papers we have counts for
5 papers · 2 filters
TextBugger: Generating Adversarial Text Against Real-world Applications
Jinfeng Li, Shouling Ji, Tianyu Du +2
Deep Learning-based Text Understanding (DLTU) is the backbone technique behind various applications, including question answering, machine translation, and text classification. Des…
Model-Reuse Attacks on Deep Learning Systems
Yujie Ji, Xinyang Zhang, Shouling Ji +2
Many of today's machine learning (ML) systems are built by reusing an array of, often pre-trained, primitive models, each fulfilling distinct functionality (e.g., feature extractio…
Interpretable Deep Learning under Fire
Xinyang Zhang, Ningfei Wang, Hua Shen +3
Providing explanations for deep neural network (DNN) models is crucial for their use in security-sensitive domains. A plethora of interpretation models have been proposed to help u…
SmartSeed: Smart Seed Generation for Efficient Fuzzing
Chenyang Lyu, Shouling Ji, Yuwei Li +3
Fuzzing is an automated application vulnerability detection method. For genetic algorithm-based fuzzing, it can mutate the seed files provided by users to obtain a number of inputs…
Differentially Private Releasing via Deep Generative Model (Technical Report)
Xinyang Zhang, Shouling Ji, Ting Wang
Privacy-preserving releasing of complex data (e.g., image, text, audio) represents a long-standing challenge for the data mining research community. Due to rich semantics of the da…