Portrait
Taifeng Liu
Ph.D. candidate
@ Xidian University @ Xidian University
Xi'an, China
Taifeng Liu

I am Taifeng Liu, a Ph.D. candidate at Xidian University, where I conduct research under the supervision of Prof. Zhuo Ma.

My research interests focus on AI security for intelligent unmanned systems, with particular emphasis on physical adversarial attacks, system security testing, and model stealing. My long-term goal is to build safer and more trustworthy intelligent systems that can operate robustly in the physical world.

Education
  • Xidian University
    Xidian University
    Advisor: Prof. Zhuo Ma
    Ph.D. Candidate in Cyberspace Security
    Sep. 2020 - Sep. 2027 (expected)
  • Xidian University
    Xidian University
    B.S. in Information Security
    Sep. 2016 - Jul. 2020
Honors & Awards
  • Outstanding Doctoral Dissertation Funding, Xidian University
    2025
  • Best Paper, Best Forum Paper, and Best Presentation Award, CCNIS
    2025
  • Second Prize, 4th China Graduate Cyberspace Security Innovation Competition (Huawei Cup)
    2025
  • QiAnXin Social Scholarship and Outstanding Graduate Student Honors
    Multiple Years
News
2025
Our paper Improving Sustainability of Adversarial Examples in Class-Incremental Learning has been accepted by AAAI 2026.
Nov 07
Our paper L-HAWK: A Controllable Physical Adversarial Patch Against a Long-Distance Target has been accepted by NDSS 2025.
Jan 31
Selected Publications (view all )
Improving Sustainability of Adversarial Examples in Class-Incremental Learning

Taifeng Liu, Xinjing Liu, Liangqiu Dong, Yang Liu, Yilong Yang, Zhuo Ma

AAAI Conference on Artificial Intelligence (AAAI) 2026 First Author Poster CCF-A

A class-incremental learning attack that strengthens the long-term sustainability of adversarial examples under increasingly difficult continual updates.

[Arxiv] [Code]

Improving Sustainability of Adversarial Examples in Class-Incremental Learning

Taifeng Liu, Xinjing Liu, Liangqiu Dong, Yang Liu, Yilong Yang, Zhuo Ma

AAAI Conference on Artificial Intelligence (AAAI) 2026 First Author Poster CCF-A

A class-incremental learning attack that strengthens the long-term sustainability of adversarial examples under increasingly difficult continual updates.

[Arxiv] [Code]

L-HAWK: A Controllable Physical Adversarial Patch Against a Long-Distance Target

Taifeng Liu, Yang Liu, Zhuo Ma, Tong Yang, Xinjing Liu, Teng Li, Jianfeng Ma

The Network and Distributed System Security Symposium (NDSS) 2025 First Author CCF-A

A controllable long-distance physical adversarial patch that attacks moving targets from over 100 meters away with strong success rates in the physical world.

[Paper] [Code]

L-HAWK: A Controllable Physical Adversarial Patch Against a Long-Distance Target

Taifeng Liu, Yang Liu, Zhuo Ma, Tong Yang, Xinjing Liu, Teng Li, Jianfeng Ma

The Network and Distributed System Security Symposium (NDSS) 2025 First Author CCF-A

A controllable long-distance physical adversarial patch that attacks moving targets from over 100 meters away with strong success rates in the physical world.

[Paper] [Code]

Model Stealing Detection for IoT Services Based on Multi-Dimensional Features

Xinjing Liu, Taifeng Liu#, Hao Yang, Jiakang Dong, Zuobin Ying, Zhuo Ma (# corresponding author)

IEEE Internet of Things Journal 2024 Corresponding Author CCF-C SCI Q2

A multi-dimensional feature based defense for detecting model stealing attempts against IoT services with low overhead in normal cloud operation.

[Paper]

Model Stealing Detection for IoT Services Based on Multi-Dimensional Features

Xinjing Liu, Taifeng Liu#, Hao Yang, Jiakang Dong, Zuobin Ying, Zhuo Ma (# corresponding author)

IEEE Internet of Things Journal 2024 Corresponding Author CCF-C SCI Q2

A multi-dimensional feature based defense for detecting model stealing attempts against IoT services with low overhead in normal cloud operation.

[Paper]

RPAU: Fooling the Eyes of UAVs via Physical Adversarial Patches

Taifeng Liu, Chao Yang, Xinjing Liu, Ruidong Han, Jianfeng Ma

IEEE Transactions on Intelligent Transportation Systems 2023 First Author CCF-B SCI Q2

A physical adversarial patch attack that misleads UAV visual perception and demonstrates effective real-world deception against airborne platforms.

[Paper]

RPAU: Fooling the Eyes of UAVs via Physical Adversarial Patches

Taifeng Liu, Chao Yang, Xinjing Liu, Ruidong Han, Jianfeng Ma

IEEE Transactions on Intelligent Transportation Systems 2023 First Author CCF-B SCI Q2

A physical adversarial patch attack that misleads UAV visual perception and demonstrates effective real-world deception against airborne platforms.

[Paper]

All publications