Search Results for author: Geguang Pu

Found 11 papers, 1 papers with code

Towards Better Fairness-Utility Trade-off: A Comprehensive Measurement-Based Reinforcement Learning Framework

no code implementations21 Jul 2023 Simiao Zhang, Jitao Bai, Menghong Guan, Yihao Huang, Yueling Zhang, Jun Sun, Geguang Pu

The results demonstrate that CFU can improve the classifier on multiple fairness metrics without sacrificing its utility.


Architecture-agnostic Iterative Black-box Certified Defense against Adversarial Patches

no code implementations18 May 2023 Di Yang, Yihao Huang, Qing Guo, Felix Juefei-Xu, Ming Hu, Yang Liu, Geguang Pu

The adversarial patch attack aims to fool image classifiers within a bounded, contiguous region of arbitrary changes, posing a real threat to computer vision systems (e. g., autonomous driving, content moderation, biometric authentication, medical imaging) in the physical world.

Autonomous Driving

Masked Faces with Faced Masks

no code implementations17 Jan 2022 JiaYi Zhu, Qing Guo, Felix Juefei-Xu, Yihao Huang, Yang Liu, Geguang Pu

Modern face recognition systems (FRS) still fall short when the subjects are wearing facial masks, a common theme in the age of respiratory pandemics.

Face Recognition

ALA: Naturalness-aware Adversarial Lightness Attack

no code implementations16 Jan 2022 Yihao Huang, Liangru Sun, Qing Guo, Felix Juefei-Xu, JiaYi Zhu, Jincao Feng, Yang Liu, Geguang Pu

To obtain adversarial examples with a high attack success rate, we propose unconstrained enhancement in terms of the light and shade relationship in images.

Adversarial Attack Denoising +2

Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network

no code implementations25 Nov 2021 Yihao Huang, Felix Juefei-Xu, Qing Guo, Geguang Pu, Yang Liu

Specifically, we propose the circle-of-confusion predictive network (CoCNet) by taking the all-in-focus image and depth image as inputs to estimate circle-of-confusion parameters for each pixel, which are employed to render the final image through a well-known physical model of bokeh.

Adversarial Attack Deblurring +1

AdvFilter: Predictive Perturbation-aware Filtering against Adversarial Attack via Multi-domain Learning

no code implementations14 Jul 2021 Yihao Huang, Qing Guo, Felix Juefei-Xu, Lei Ma, Weikai Miao, Yang Liu, Geguang Pu

To this end, we first comprehensively investigate two kinds of pixel denoising methods for adversarial robustness enhancement (i. e., existing additive-based and unexplored filtering-based methods) under the loss functions of image-level and semantic-level, respectively, showing that pixel-wise filtering can obtain much higher image quality (e. g., higher PSNR) as well as higher robustness (e. g., higher accuracy on adversarial examples) than existing pixel-wise additive-based method.

Adversarial Attack Adversarial Robustness +1

Dodging DeepFake Detection via Implicit Spatial-Domain Notch Filtering

no code implementations19 Sep 2020 Yihao Huang, Felix Juefei-Xu, Qing Guo, Yang Liu, Geguang Pu

We first demonstrate that frequency-domain notch filtering, although famously shown to be effective in removing periodic noise in the spatial domain, is infeasible for our task at hand due to the manual designs required for the notch filters.

DeepFake Detection Face Swapping +2

FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction

1 code implementation13 Jun 2020 Yihao Huang, Felix Juefei-Xu, Run Wang, Qing Guo, Lei Ma, Xiaofei Xie, Jianwen Li, Weikai Miao, Yang Liu, Geguang Pu

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.

DeepFake Detection Face Swapping +2

FakeLocator: Robust Localization of GAN-Based Face Manipulations

no code implementations27 Jan 2020 Yihao Huang, Felix Juefei-Xu, Qing Guo, Yang Liu, Geguang Pu

In this work, we investigate the architecture of existing GAN-based face manipulation methods and observe that the imperfection of upsampling methods therewithin could be served as an important asset for GAN-synthesized fake image detection and forgery localization.

Data Augmentation Face Generation +3

LTLf Synthesis with Fairness and Stability Assumptions

no code implementations17 Dec 2019 Shufang Zhu, Giuseppe De Giacomo, Geguang Pu, Moshe Vardi

A key observation here is that even if we consider systems with LTLf goals on finite traces, environment assumptions need to be expressed over infinite traces, since accomplishing the agent goals may require an unbounded number of environment action.


Symbolic LTLf Synthesis

no code implementations23 May 2017 Shufang Zhu, Lucas M. Tabajara, Jianwen Li, Geguang Pu, Moshe Y. Vardi

LTLf synthesis is the process of finding a strategy that satisfies a linear temporal specification over finite traces.

Cannot find the paper you are looking for? You can Submit a new open access paper.