← Authors

Tianyu Pang

56 papers · 2018–2025 · 8 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (7) 🐝 Cross-Pollinator (13) πŸ—ΊοΈ Taxonomy Completionist (58) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (9) 🌍 Conference Polyglot (8) 🀝 Dynamic Duo (32) πŸ‘‘ Triple Crown πŸ”¬ Deep Specialist (19) πŸ† Keyword Champion (2) πŸ—ƒοΈ Keyword Collector (149) ⚑ Prolific Year (9) πŸ”₯ Unstoppable (8) πŸ’Ž Century Club (56)

Conferences

NIPS (15) ICML (14) ICLR (13) CVPR (7) ICCV (3) ECCV (2) ACL (1) EMNLP (1)

Top co-authors

Chao Du (32) Min Lin (23) Jun Zhu (20) Yinpeng Dong (16) Hang Su (13) Qian Liu (12) Xiao Yang (10) Shuicheng Yan (9) Chongxuan Li (6) Zhijie Deng (5)

Research topics

Privacy (2)

Keywords

adversarial robustness (10) adversarial learning (7) adversarial training (7) diffusion model (5) adversarial attack (5) adversarial defense (4) neural network (4) adversarial example (4) image generation (3) image classification (3) backdoor attack (3) black-box attack (3) deep equilibrium model (2) few-shot learning (2) generative model (2) language model (2) policy optimization (2) robust optimization (2) score matching (2) model compression (2)

Papers

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models ICLR 2025
Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift CVPR 2025
Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts ICCV 2025
Scaling up Masked Diffusion Models on Text ICLR 2025
RegMix: Data Mixture as Regression for Language Model Pre-training ICLR 2025
When Attention Sink Emerges in Language Models: An Empirical View ICLR 2025
Bootstrapping Language Models with DPO Implicit Rewards ICLR 2025
Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates ICLR 2025
A Closer Look at Machine Unlearning for Large Language Models ICLR 2025
Improving Long-Text Alignment for Text-to-Image Diffusion Models ICLR 2025
Unnatural Languages Are Not Bugs but Features for LLMs ICML 2025
BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms ICML 2025
LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning ICML 2025
Improving Your Model Ranking on Chatbot Arena by Vote Rigging ICML 2025
Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models ICML 2025
Weak-to-Strong Jailbreaking on Large Language Models ICML 2025
Model Balancing Helps Low-data Training and Fine-tuning EMNLP 2024
Intriguing Properties of Data Attribution on Diffusion Models ICLR 2024
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses NIPS 2024
Graph Diffusion Policy Optimization NIPS 2024
Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs NIPS 2024
Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning ACL 2024
Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast ICML 2024
Finetuning Text-to-Image Diffusion Models for Fairness ICLR 2024
BAFFLE: A Baseline of Backpropagation-Free Federated Learning ECCV 2024
Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows ICML 2023
Exploring Incompatible Knowledge Transfer in Few-Shot Image Generation CVPR 2023
Better Diffusion Models Further Improve Adversarial Training ICML 2023
Improving Adversarial Robustness of Deep Equilibrium Models with Explicit Regulations Along the Neural Dynamics ICML 2023
Bag of Tricks for Training Data Extraction from Language Models ICML 2023
Gaussian Mixture Solvers for Diffusion Models NIPS 2023
On Calibrating Diffusion Probabilistic Models NIPS 2023
On Evaluating Adversarial Robustness of Large Vision-Language Models NIPS 2023
Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training NIPS 2023
Efficient Diffusion Policies For Offline Reinforcement Learning NIPS 2023
Robustness and Accuracy Could Be Reconcilable by (Proper) Definition ICML 2022
Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks ECCV 2022
Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022
Exploring Memorization in Adversarial Training ICLR 2022
A Closer Look at the Adversarial Robustness of Deep Equilibrium Models NIPS 2022
Accumulative Poisoning Attacks on Real-time Data NIPS 2021
Towards Face Encryption by Generating Adversarial Identity Masks ICCV 2021
Bag of Tricks for Adversarial Training ICLR 2021
Black-Box Detection of Backdoor Attacks With Limited Information and Data ICCV 2021
Adversarial Distributional Training for Robust Deep Learning NIPS 2020
Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness ICLR 2020
Benchmarking Adversarial Robustness on Image Classification CVPR 2020
Boosting Adversarial Training with Hypersphere Embedding NIPS 2020
Efficient Learning of Generative Models via Finite-Difference Score Matching NIPS 2020
Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks CVPR 2019
Improving Black-box Adversarial Attacks with a Transfer-based Prior NIPS 2019
Improving Adversarial Robustness via Promoting Ensemble Diversity ICML 2019
Boosting Adversarial Attacks With Momentum CVPR 2018
Towards Robust Detection of Adversarial Examples NIPS 2018
Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser CVPR 2018
Max-Mahalanobis Linear Discriminant Analysis Networks ICML 2018