About/ Publications/ Pixel Privacy Gallery/ Talks

Zhuoran Liu

I am a postdoc in the Digital Security group at Radboud University working with Prof. Lejla Batina. Before, a PhD student at the Data Science group advised by Prof. Martha Larson. Before that, I worked as a junior researcher. I'm interested in multimedia privacy and security with a focus on side-channel analysis and adversarial machine learning.

From 2018 to 2020, we organized the Pixel Privacy task in MediaEval multimedia benchmark. The objective of Pixel Privacy is to promote the innovation of protective technologies that make it safer to share social multimedia online.

Email  /  GitHub  /  Google Scholar  /  Twitter

profile photo
Main Publications

BAN: Detecting Backdoors Activated by Adversarial Neuron Noise
Xiaoyun Xu, Zhuoran Liu, Stefanos Koffas, Shujian Yu, Stjepan Picek
Advances in Neural Information Processing Systems (NeurIPS), 2024

SoK: Neural Network Extraction Through Physical Side Channels
Péter Horváth, Dirk Lauret, Zhuoran Liu, Lejla Batina
USENIX Security Symposium, 2024

Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression
Zhuoran Liu, Zhengyu Zhao, Martha Larson
International Conference on Machine Learning (ICML), 2023

[Code]

Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?
Rui Wen, Zhengyu Zhao, Zhuoran Liu, Michael Backes, Tianhao Wang, Yang Zhang
International Conference on Learning Representations (ICLR) (Spotlight), 2023


Going Grayscale: The Road to Understanding and Improving Unlearnable Examples
Zhuoran Liu, Zhengyu Zhao, Alex Kolmus, Tijn Berns, Twan van Laarhoven, Tom Heskes, Martha Larson
arXiv, 2021

[Code]

Textual Concept Expansion with Commonsense Knowledge to Improve Dual-Stream Image-Text Matching
Mingliang Liang, Zhuoran Liu, Martha Larson
International Conference On Multimedia Modeling (MMM), 2023

[Code]

Generative Poisoning Using Random Discriminators
Dirren van Vlijmen, Alex Kolmus, Zhuoran Liu, Zhengyu Zhao, Martha Larson
Responsible Computer Vision Workshop at European Conference on Computer Vision (ECCV), 2022


On Success and Simplicity: A Second Look at Transferable Targeted Attacks
Zhengyu Zhao, Zhuoran Liu, Martha Larson
Advances in Neural Information Processing Systems (NeurIPS), 2021

[Code]

Simple yet powerful transferable targeted attacks.

Pivoting Image-based Profiles Toward Privacy: Inhibiting Malicious Profiling with Adversarial Additions
Zhuoran Liu, Zhengyu Zhao, Martha Larson
International Conference on User Modeling, Adaptation and Personalization (UMAP), 2021

[Code to appear]

Adversarial Item Promotion: Vulnerabilities at the Core of Top-N Recommenders that Use Images to Address Cold Start
Zhuoran Liu, Martha Larson
The Web Conference (WWW), 2021

[Code][Video][Slides]

Adversarial embedding attack that promotes cold item in image-aware recommenders.

Screen Gleaning: A Screen Reading TEMPEST Attack on Mobile Devices Exploiting an Electromagnetic Side Channel
Zhuoran Liu, Niels Samwel, Léo Weissbart, Zhengyu Zhao, Dirk Lauret, Lejla Batina, Martha Larson
Network and Distributed System Security Symposium (NDSS), 2021

[Code][Video][LASER21 Workshop]

TEMPEST attack to read phone screen without visual line of sight boosted by machine learning.

Adversarial Robustness Against Image Color Transformation within Parametric Filter Space
Zhengyu Zhao, Zhuoran Liu, Martha Larson
British Machine Vision Conference (BMVC), 2020
Journal version under rerview
[Code]

Generate unrestricted adversarial images by a parametric color filter.

Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distance
Zhengyu Zhao, Zhuoran Liu, Martha Larson
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[Code]

Generate large yet imperceptible adversarial images by leveraging perceptual color distance.

Who’s Afraid of Adversarial Queries? The Impact of Image Modifications on Content-based Image Retrieval
Zhuoran Liu, Zhengyu Zhao, Martha Larson
International Conference on Multimedia Retrieval (ICMR), 2019
[Code]

Adversarial image queries in content-based image retrieval system.

Other Publications

Zhuoran Liu, Zhengyu Zhao, Martha Larson, Laurent Amsaleg Exploring Quality Camouflage for Social Images, MediaEval Workshop, 2020.
Zhuoran Liu, Zhengyu Zhao, Martha Larson, Pixel Privacy 2019: Protecting Sensitive Scene Information in Images, MediaEval Workshop, 2019.
Zhuoran Liu, Zhengyu Zhao, Adversarial Photo Frame: Concealing Sensitive Scene Information of Social Images in a User-Acceptable Manner, MediaEval Workshop, 2019. [Slides]
Zhengyu Zhao, Zhuoran Liu, Martha Larson, Ahmet Iscen, Naoko Nitta Reproducible Experiments on Adaptive Discriminative Region Discovery for Scene Recognition, Reproducibility@ACM MM, 2019. [Code]
Martha Larson, Zhuoran Liu, Simon Brugman, Zhengyu Zhao, Pixel Privacy: Increasing Image Appeal while Blocking Automatic Inference of Sensitive Scene Information, MediaEval Workshop, 2018. [Slides]
Zhuoran Liu, Zhengyu Zhao, First Steps in Pixel Privacy: Exploring Deep Learning-based Image Enhancement against Large-Scale Image Inference, MediaEval Workshop, 2018.
Professional Activities:
Program Committee/Reviewer: AAAI, AISTATS, BMVC, CVPR, ECCV, FAccT, ICCV, ICLR, NeurIPS, TIFS, TPAMI, USENIX Security AEC
External Reviewer: IEEE S&P, NDSS, USENIX Security
Organization Committee: Pixel Privacy Task @MediaEval, ACM Multimedia

Amazing template from Jon Barron