PPaperPicks

Jian Lou

Sun Yat-sen University, School of Software Engineering, Zhuhai, China

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

DBLP profile ↗ORCID 0000-0002-4110-2068 ↗Homepage ↗

Venues

AAAI ×3ICML ×3ACL ×2ACM MM ×1CIKM ×1CVPR ×1ECAI ×1EMNLP ×1IJCAI ×1NeurIPS ×1SIGMOD ×1WWW ×1

Frequent coauthors

Kejia Chen
DBLP profile ↗ORCID search ↗
×2
Yulin Jin
DBLP profile ↗ORCID search ↗
×1
Fenghua Weng
DBLP profile ↗ORCID search ↗
×1
Yuecheng Li
DBLP profile ↗ORCID search ↗
×1
Hong-Kyu Lee
DBLP profile ↗ORCID search ↗
×1
Yukai Zhou
DBLP profile ↗ORCID search ↗
×1
Zhuomin Chen
DBLP profile ↗ORCID search ↗
×1
Chenyang Zhang
DBLP profile ↗ORCID search ↗
×1
Haoyu Tong
DBLP profile ↗ORCID search ↗
×1
Qiuchen Zhang
DBLP profile ↗ORCID search ↗
×1
Wenjie Wang
DBLP profile ↗ORCID search ↗
×1
Xiaochen Li
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Stochastic Universal Adversarial Perturbations with Fixed Optimization Constraint and Ensured High-probability Transferability
    AAAI 2026 ·
    Yulin Jin
    DBLP profile ↗ORCID search ↗
  2. Token-level Inference-Time Alignment for Vision-Language Models
    ACL 2026 ·
    Kejia Chen
    DBLP profile ↗ORCID search ↗
  3. Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training
    EMNLP 2025 ·
    Fenghua Weng
    DBLP profile ↗ORCID search ↗
  4. Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
    ICML 2025 ·
    Kejia Chen
    DBLP profile ↗ORCID search ↗
  5. Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
    ICML 2025 ·
    Yuecheng Li
    DBLP profile ↗ORCID search ↗
  6. Contrastive Unlearning: A Contrastive Approach to Machine Unlearning
    IJCAI 2025 ·
    Hong-Kyu Lee
    DBLP profile ↗ORCID search ↗
  7. Don't Say No: Jailbreaking LLM by Suppressing Refusal
    ACL 2025 ·
    Yukai Zhou
    DBLP profile ↗ORCID search ↗
  8. Integrating Time Series into LLMs via Multi-layer Steerable Embedding Fusion for Enhanced Forecasting
    CIKM 2025 ·
    Zhuomin Chen
    DBLP profile ↗ORCID search ↗
  9. PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models
    ICML 2025 ·
    Chenyang Zhang
    DBLP profile ↗ORCID search ↗
  10. Balancing Generalization and Robustness in Adversarial Training via Steering through Clean and Adversarial Gradient Directions
    ACM MM 2024 ·
    Haoyu Tong
    DBLP profile ↗ORCID search ↗
  11. DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy
    WWW 2024 ·
    Qiuchen Zhang
    DBLP profile ↗ORCID search ↗
  12. IGAMT: Privacy-Preserving Electronic Health Record Synthesization with Heterogeneity and Irregularity
    AAAI 2024 ·
    Wenjie Wang
    DBLP profile ↗ORCID search ↗
  13. Local Differentially Private Heavy Hitter Detection in Data Streams with Bounded Memory
    SIGMOD 2024 ·
    Xiaochen Li
    DBLP profile ↗ORCID search ↗
  14. Physical Backdoor: Towards Temperature-Based Backdoor Attacks in the Physical World
    CVPR 2024 ·
    Wen Yin
    DBLP profile ↗ORCID search ↗
  15. Rapid Plug-in Defenders
    NeurIPS 2024 ·
    Kai Wu
    DBLP profile ↗ORCID search ↗
  16. SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models
    ECAI 2024 ·
    Jiawen Zhang
    DBLP profile ↗ORCID search ↗
  17. Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-Time Dynamics
    AAAI 2024 ·
    Lanlan Chen
    DBLP profile ↗ORCID search ↗