activity
20242026
most citedT2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models

2 citations · 3 across the 8 of their papers we have counts for

collaborators

13 papers

cs.LG2026

Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information

Yifan Zhu, Yibo Miao, Yinpeng Dong +1

The volume of freely scraped data on the Internet has driven the tremendous success of deep learning. Along with this comes the growing concern about data privacy and security. Num…

cs.LG2025

Analyzing the Power of Chain of Thought through Memorization Capabilities

Lijia Yu, Xiao-Shan Gao, Lijun Zhang

It has been shown that the chain of thought (CoT) can enhance the power of large language models (LLMs) to solve certain mathematical reasoning problems. However, the capacity of C…

cs.CR2025

Provable Watermarking for Data Poisoning Attacks

Yifan Zhu, Lijia Yu, Xiao-Shan Gao

In recent years, data poisoning attacks have been increasingly designed to appear harmless and even beneficial, often with the intention of verifying dataset ownership or safeguard…

cs.LG2025

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling

Yichuan Cao, Yibo Miao, Xiao-Shan Gao +1

Text-to-image (T2I) models raise ethical and safety concerns due to their potential to generate inappropriate or harmful images. Evaluating these models' security through red-teami…

cs.LG2025

Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization

Shuang Liu, Yihan Wang, Yifan Zhu +2

Wasserstein distributionally robust optimization (WDRO) optimizes against worst-case distributional shifts within a specified uncertainty set, leading to enhanced generalization on…

cs.LG2025

Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability

Lijia Yu, Yibo Miao, Yifan Zhu +2

The primary objective of learning methods is generalization. Classic uniform generalization bounds, which rely on VC-dimension or Rademacher complexity, fail to explain the signifi…