PPaperPicks

Wenjie Ruan

University of Exeter, UK

17 papers at tracked venues · 13 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-8311-8738 ↗Google Scholar ↗Homepage ↗

Venues

AAAI ×4NeurIPS ×3ACL ×2CVPR ×2ECCV ×1EMNLP ×1ICCV ×1ICDM ×1ICML ×1IJCAI ×1

Frequent coauthors

Zhen Chen
DBLP profile ↗ORCID search ↗
×2
Yi Zhang
DBLP profile ↗ORCID search ↗
×2
Xiangyu Yin
DBLP profile ↗ORCID search ↗
×2
Ruiyang Ni
DBLP profile ↗ORCID search ↗
×1
Shuaibiao Han
DBLP profile ↗ORCID search ↗
×1
Fu Wang
DBLP profile ↗ORCID search ↗
×1
Jinwei Hu
DBLP profile ↗ORCID search ↗
×1
Ghazal Lalooha
DBLP profile ↗ORCID search ↗
×1
Siqi Sun
DBLP profile ↗ORCID search ↗
×1
Tianle Zhang
DBLP profile ↗ORCID search ↗
×1
Yi Dong
DBLP profile ↗ORCID search ↗
×1
Ronghui Mu
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Defending LLMs against Jailbreak Attacks via Template-Based ICL with a Defensive Suffix
    ACL 2026 ·
    Ruiyang Ni
    DBLP profile ↗ORCID search ↗
  2. Dictionary Guided Sparse Logit Editing for Reliable Jailbreak Attacks
    ACL 2026 ·
    Shuaibiao Han
    DBLP profile ↗ORCID search ↗
  3. Fragile by Design: On the Limits of Adversarial Defenses in Personalized DreamBooth Generation
    AAAI 2026 ·
    Zhen Chen
    DBLP profile ↗ORCID search ↗
  4. A Black-Box Evaluation Framework for Semantic Robustness in Bird's Eye View Detection
    AAAI 2025 ·
    Fu Wang
    DBLP profile ↗ORCID search ↗
  5. Adversarial Training for Probabilistic Robustness
    ICCV 2025 ·
    Yi Zhang
    DBLP profile ↗ORCID search ↗
  6. FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model
    NeurIPS 2025 ·
    Jinwei Hu
    DBLP profile ↗ORCID search ↗
  7. FAP: A Foveation-Inspired Adversarial Purification Pipeline for Enhancing Robustness in Mammography Classification
    ICDM 2025 ·
    Ghazal Lalooha
    DBLP profile ↗ORCID search ↗
  8. Boosting Adversarial Training via Fisher-Rao Norm-Based Regularization
    CVPR 2024 ·
    Xiangyu Yin
    DBLP profile ↗ORCID search ↗
  9. CROWD: Certified Robustness via Weight Distribution for Smoothed Classifiers against Backdoor Attack
    EMNLP 2024 ·
    Siqi Sun
    DBLP profile ↗ORCID search ↗
  10. PRASS: Probabilistic Risk-averse Robust Learning with Stochastic Search
    IJCAI 2024 ·
    Tianle Zhang
    DBLP profile ↗ORCID search ↗
  11. Position: Building Guardrails for Large Language Models Requires Systematic Design
    ICML 2024 ·
    Yi Dong
    DBLP profile ↗ORCID search ↗
  12. ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models Against Stochastic Perturbation
    ECCV 2024 ·
    Yi Zhang
    DBLP profile ↗ORCID search ↗
  13. Representation-Based Robustness in Goal-Conditioned Reinforcement Learning
    AAAI 2024 ·
    Xiangyu Yin
    DBLP profile ↗ORCID search ↗
  14. Reward Certification for Policy Smoothed Reinforcement Learning
    AAAI 2024 ·
    Ronghui Mu
    DBLP profile ↗ORCID search ↗
  15. TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
    NeurIPS 2024 ·
    Zhen Chen
    DBLP profile ↗ORCID search ↗
  16. The Implicit Bias of Gradient Descent toward Collaboration between Layers: A Dynamic Analysis of Multilayer Perceptions
    NeurIPS 2024 ·
    Zheng Wang
    DBLP profile ↗ORCID search ↗
  17. Towards Fairness-Aware Adversarial Learning
    CVPR 2024 ·
    Yanghao Zhang
    DBLP profile ↗ORCID search ↗