Publications

• On the Difficulty of Defending Contrastive Learning against Backdoor Attacks
  Changjiang Li, Ren Pang, Bochuan Cao, Jinghui Chen, Shouling Ji, Ting Wang
  USENIX Security’24
  

• Defending Pre-trained Language Models as Few-shot Learners Against Backdoor Attacks
  Zhaohan Xi, Tianyu Du, Changjiang Li, Ren Pang, Shouling Ji, Jinghui Chen, Fenglong Ma, Ting Wang
  NeurIPS’23
  

• An Embarrassingly Simple Backdoor Attack against Self-supervised Learning
  Changjiang Li, Ren Pang, Zhaohan Xi, Tianyu Du, Shouling Ji, Yuan Yao, Ting Wang
  ICCV’23
  

• On the Security Risks of Knowledge Graph Reasoning
  Zhaohan Xi, Tianyu Du, Changjiang Li, Ren Pang, Shouling Ji, Xiapu Luo, Xusheng Xiao, Fenglong Ma, Ting Wang
  USENIX Security’23
  

• The Dark Side of AutoML: Towards Architectural Backdoor Search
  Ren Pang, Changjiang Li, Zhaohan Xi, Shouling Ji, Ting Wang
  ICLR’23
  

• TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors
  Ren Pang, Zheng Zhang, Xiangshan Gao, Zhaohan Xi, Shouling Ji, Cheng Peng, Ting Wang
  IEEE EuroS&P’22
  

• On the Security Risks of AutoML
  Ren Pang, Zhaohan Xi, Shouling Ji, Xiapu Luo, Ting Wang
  USENIX Security’22
  

• Graph Backdoor
  Zhaohan Xi, Ren Pang, Shouling Ji, Ting Wang
  USENIX Security’21
  

• i-Algebra: Towards Interactive Interpretability of Neural Nets
  Xinyang Zhang, Ren Pang, Shouling Ji, Fenglong Ma, Ting Wang
  AAAI’21
  

• AdvMind: Inferring Adversary Intent of Black-Box Attacks
  Ren Pang, Xinyang Zhang, Shouling Ji, Xiapu Luo, Ting Wang
  ACM KDD’20
  

• A Tale of Evil Twins: Adversarial Inputs versus Poisoned Models
  Ren Pang, Hua Shen, Xinyang Zhang, Shouling Ji, Yevgeniy Vorobeychik, Xiapu Luo, Alex Liu, Ting Wang
  ACM CCS’20