Scholar
Yinpeng Dong
Google Scholar ID: 6_4ad84AAAAJ
Tsinghua University
Machine Learning
Deep Learning
AI Safety
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
12,690
H-index
41
i10-index
69
Publications
20
Co-authors
6
list available
Contact
Email
dongyinpeng@gmail.com
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
Publications
30 items
Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification
2026
Cited
0
Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information
2026
Cited
0
MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
2026
Cited
0
Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models
2026
Cited
0
Vibe Reasoning: Eliciting Frontier AI Mathematical Capabilities -- A Case Study on IMO 2025 Problem 6
2025
Cited
0
DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios
2025
Cited
0
Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention
2025
Cited
0
Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models
2025
Cited
0
Load more
Resume (English only)
Academic Achievements
Named in the Stanford/Elsevier list of World's Top 2% Scientists (single-year impact, 2023) in Dec 2024 and Oct 2023
PhD thesis 'Adversarial Attacks and Robustness Evaluation in Deep Learning' awarded the CCF Outstanding Doctoral Dissertation Award (2022)
Paper 'BadDet: Backdoor Attacks on Object Detection' received Best Paper Award at ECCV 2022 Workshop on Adversarial Robustness in the Real World
Serving as Area Chair for ICML 2025 and ICLR 2025
Paper 'Omniview-Tuning' accepted as Oral presentation at ECCV 2024
Led the open-sourcing of MultiTrust, a comprehensive benchmark for trustworthiness evaluation of multimodal large language models (2024)
Multiple papers accepted at NeurIPS 2024, including MultiTrust, T2VSafetyBench, and 'Diffusion Models are Certifiably Robust Classifiers'
Invited talk at ECCV 2024 Workshop on The Dark Side of Generative AIs and Beyond (Sep 2024)
Organizing workshop 'Test-time Scaling for Computer Vision' at CVPR 2025
Co-authors
6 total
Jun Zhu
Professor of Computer Science, Tsinghua University
Hang Su
Associated Professor, Tsinghua University
Tianyu Pang
Senior Research Scientist, Sea AI Lab
Xiao Yang
Tsinghua University
Jianguo Li
Director, Ant Group
Zhijie Deng
Assistant Professor, Shanghai Jiao Tong University
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up