Scholar
Zhuoran Liu
Google Scholar ID: 9U3aIWsAAAAJ
Radboud University
Citations & Impact
Citations
747
H-index
11
i10-index
11
Publications
20
Co-authors
19
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published 'Towards Backdoor Stealthiness in Model Parameter Space' at ACM CCS 2025
- Published 'Resisting Bag-based Attribute Profiling by Adding Adversarial Items to Existing Media Profiles' in IEEE TIFS 2025
- Published 'BAN: Detecting Backdoors Activated by Adversarial Neuron Noise' at NeurIPS 2024
- Published 'SoK: Neural Network Extraction Through Physical Side Channels' at USENIX Security Symposium 2024
- Published 'Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression' at ICML 2023
- Published 'Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?' at ICLR 2023 (Spotlight)
- Published 'Adversarial Item Promotion: Vulnerabilities at the Core of Top-N Recommenders that Use Images to Address Cold Start' at The Web Conference (WWW) 2021
- Published 'Screen Gleaning: A Screen Reading TEMPEST Attack on Mobile Devices Exploiting an Electromagnetic Side Channel' at NDSS 2021
- Published 'Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distance' at CVPR 2020
- Multiple papers include open-source code; some accompanied by videos or slides
