PPaperPicks

Xiangyu Zhang

Purdue University, West Lafayette, IN, USA

26 papers at tracked venues · 21 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-9544-2500 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×8ACL ×3ICML ×3AAAI ×2CVPR ×2EMNLP ×2ICLR ×2ECCV ×1ICCV ×1IROS ×1WACV ×1

Frequent coauthors

Hanxi Guo
DBLP profile ↗ORCID search ↗
×3
Siyuan Cheng
DBLP profile ↗ORCID search ↗
×3
Shiwei Feng
DBLP profile ↗ORCID search ↗
×2
Xuan Chen
DBLP profile ↗ORCID search ↗
×2
Zhiyuan Cheng
DBLP profile ↗ORCID search ↗
×2
Chengpeng Wang
DBLP profile ↗ORCID search ↗
×2
Guanhong Tao
DBLP profile ↗ORCID search ↗
×1
Yifei Gao
DBLP profile ↗ORCID search ↗
×1
Danning Xie
DBLP profile ↗ORCID search ↗
×1
Yuan Zhou
DBLP profile ↗ORCID search ↗
×1
Xiaolong Jin
DBLP profile ↗ORCID search ↗
×1
Nan Jiang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening
    WACV 2026 ·
    Guanhong Tao
    DBLP profile ↗ORCID search ↗
  2. Poisoning with a Pill: Circumventing Detection in Federated Learning
    AAAI 2026 ·
    Hanxi Guo
    DBLP profile ↗ORCID search ↗
  3. Raw Pointer Rewriting with LLMs for Translating C to Safer Rust
    ACL 2026 ·
    Yifei Gao
    DBLP profile ↗ORCID search ↗
  4. CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI
    CVPR 2025 ·
    Siyuan Cheng
    DBLP profile ↗ORCID search ↗
  5. CoRe: Benchmarking LLMs' Code Reasoning Capabilities through Static Analysis Tasks
    NeurIPS 2025 ·
    Danning Xie
    DBLP profile ↗ORCID search ↗
  6. EffiTune: Diagnosing and Mitigating Training Inefficiency for Parameter Tuner in Robot Navigation System
    IROS 2025 ·
    Shiwei Feng
    DBLP profile ↗ORCID search ↗
  7. Exploiting the Shadows: Unveiling Privacy Leaks through Lower-Ranked Tokens in Large Language Models
    ACL 2025 ·
    Yuan Zhou
    DBLP profile ↗ORCID search ↗
  8. JailbreakDiffBench: A Comprehensive Benchmark for Jailbreaking Diffusion Models
    ICCV 2025 ·
    Xiaolong Jin
    DBLP profile ↗ORCID search ↗
  9. Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning
    ICLR 2025 ·
    Nan Jiang
    DBLP profile ↗ORCID search ↗
  10. ProSec: Fortifying Code LLMs with Proactive Security Alignment
    ICML 2025 ·
    Xiangzhe Xu
    DBLP profile ↗ORCID search ↗
  11. Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis
    EMNLP 2025 ·
    Hanxi Guo
    DBLP profile ↗ORCID search ↗
  12. RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
    ICML 2025 ·
    Jinyao Guo
    DBLP profile ↗ORCID search ↗
  13. System Prompt Hijacking via Permutation Triggers in LLM Supply Chains
    ACL 2025 ·
    Lu Yan
    DBLP profile ↗ORCID search ↗
  14. TAI3: Testing Agent Integrity in Interpreting User Intent
    NeurIPS 2025 ·
    Shiwei Feng
    DBLP profile ↗ORCID search ↗
  15. Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
    NeurIPS 2025 ·
    Xuan Chen
    DBLP profile ↗ORCID search ↗
  16. VERA: Variational Inference Framework for Jailbreaking Large Language Models
    NeurIPS 2025 ·
    Anamika Lochab
    DBLP profile ↗ORCID search ↗
  17. BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
    ICML 2024 ·
    Zhiyuan Cheng
    DBLP profile ↗ORCID search ↗
  18. BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens
    NeurIPS 2024 ·
    Hanxi Guo
    DBLP profile ↗ORCID search ↗
  19. Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
    AAAI 2024 ·
    Shengwei An
    DBLP profile ↗ORCID search ↗
  20. Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection
    ICLR 2024 ·
    Zhiyuan Cheng
    DBLP profile ↗ORCID search ↗
  21. LLMDFA: Analyzing Dataflow in Code with Large Language Models
    NeurIPS 2024 ·
    Chengpeng Wang
    DBLP profile ↗ORCID search ↗
  22. Lotus: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
    CVPR 2024 ·
    Siyuan Cheng
    DBLP profile ↗ORCID search ↗
  23. Sanitizing Large Language Models in Bug Detection with Data-Flow
    EMNLP 2024 ·
    Chengpeng Wang
    DBLP profile ↗ORCID search ↗
  24. Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
    NeurIPS 2024 ·
    Zian Su
    DBLP profile ↗ORCID search ↗
  25. UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
    ECCV 2024 ·
    Siyuan Cheng
    DBLP profile ↗ORCID search ↗
  26. When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search
    NeurIPS 2024 ·
    Xuan Chen
    DBLP profile ↗ORCID search ↗