activity
20122022
most citedFakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction

6 citations · 13 across the 5 of their papers we have counts for

collaborators

6 papers

cs.SE2022

Identifying Boundary Conditions with the Syntax and Semantic Information of Goals

Yechuan Xia, Jianwen Li, Shengping Xiao +2

In goal-oriented requirement engineering, boundary conditions(BC) are used to capture the divergence of goals, i.e., goals cannot be satisfied as a whole in some circumstances. As…

cs.AI20212 cited

Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learning

Peng Jin, Min Zhang, Jianwen Li +2

Formally verifying Deep Reinforcement Learning (DRL) systems is a challenging task due to the dynamic continuity of system behaviors and the black-box feature of embedded neural ne…

cs.CV20206 cited

FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction

Yihao Huang, Felix Juefei-Xu, Run Wang +7

At this moment, GAN-based image generation methods are still imperfect, whose upsampling design has limitations in leaving some certain artifact patterns in the synthesized image.…

cs.LO2018

SAT-based Explicit LTLf Satisfiability Checking

Jianwen Li, Kristin Y. Rozier, Geguang Pu +2

We present here a SAT-based framework for LTLf (Linear Temporal Logic on Finite Traces) satisfiability checking. We use propositional SAT-solving techniques to construct a transiti…

cs.LO20134 cited

MDM: A Mode Diagram Modeling Framework

Zheng Wang, Geguang Pu, Jianwen Li +5

Periodic control systems used in spacecrafts and automotives are usually period-driven and can be decomposed into different modes with each mode representing a system state observe…

cs.FL20121 cited

On the Relationship between LTL Normal Forms and Buechi Automata

Jianwen Li, Geguang Pu, Lijun Zhang +3

In this paper, we consider the problem of translating LTL formulas to Buechi automata. We first translate the given LTL formula into a special disjuctive-normal form (DNF). The for…