2 citations · 9 across the 18 of their papers we have counts for
21 papers
On the Turing Completeness of Transformers and Agents
Yimu Qiao, Lijia Yu, Ruichen Qiu +1
Transformers have emerged as the dominant architecture in sequence modeling, achieving remarkable success in natural language processing and reasoning tasks. While existing literat…
Once Poisoned, Arbitrarily Controlled: A Programmable Backdoor in VLMs
Tao Lin, Gaojie Jin, Zongxin Liu +2
Existing vision-language model (VLM) backdoors are usually treated as static vulnerabilities: one-to-one and N-to-N attacks bind one or more triggers to a finite set of targets bef…
Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction
Lijia Yu, Jiuxin Cao, Yuchen Qiang +3
Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness. A key property is cross-model transferabilit…
Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
Gaojie Jin, Yong Tao, Lijia Yu +1
Jung et al. (2025) introduce a hypothesis testing framework for guaranteeing agreement between large language models (LLMs) and human judgments, relying on the assumption that the…
BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models
Shuaitong Liu, Renjue Li, Lijia Yu +3
Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have also introduced their computati…
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…
SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG
Xiaonan Si, Meilin Zhu, Simeng Qin +7
Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but are vulnerable to corpus poisoning and contamination attacks, which ca…
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…
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…
PowerMLP: An Efficient Version of KAN
Ruichen Qiu, Yibo Miao, Shiwen Wang +3
The Kolmogorov-Arnold Network (KAN) is a new network architecture known for its high accuracy in several tasks such as function fitting and PDE solving. The superior expressive cap…
Generalizability of Memorization Neural Networks
Lijia Yu, Xiao-Shan Gao, Lijun Zhang +1
The neural network memorization problem is to study the expressive power of neural networks to interpolate a finite dataset. Although memorization is widely believed to have a clos…
Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors
Tao Lin, Lijia Yu, Gaojie Jin +3
In recent years, the study of adversarial robustness in object detection systems, particularly those based on deep neural networks (DNNs), has become a pivotal area of research. Tr…
T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
Yibo Miao, Yifan Zhu, Yinpeng Dong +3
The recent development of Sora leads to a new era in text-to-video (T2V) generation. Along with this comes the rising concern about its security risks. The generated videos may con…
Generalization Bound and New Algorithm for Clean-Label Backdoor Attack
Lijia Yu, Shuang Liu, Yibo Miao +2
The generalization bound is a crucial theoretical tool for assessing the generalizability of learning methods and there exist vast literatures on generalizability of normal learnin…
Detection and Defense of Unlearnable Examples
Yifan Zhu, Lijia Yu, Xiao-Shan Gao
Privacy preserving has become increasingly critical with the emergence of social media. Unlearnable examples have been proposed to avoid leaking personal information on the Interne…
Restore Translation Using Equivariant Neural Networks
Yihan Wang, Lijia Yu, Xiao-Shan Gao
Invariance to spatial transformations such as translations and rotations is a desirable property and a basic design principle for classification neural networks. However, the commo…
Achieve Optimal Adversarial Accuracy for Adversarial Deep Learning using Stackelberg Game
Xiao-Shan Gao, Shuang Liu, Lijia Yu
Adversarial deep learning is to train robust DNNs against adversarial attacks, which is one of the major research focuses of deep learning. Game theory has been used to answer some…
Adversarial Parameter Attack on Deep Neural Networks
Lijia Yu, Yihan Wang, Xiao-Shan Gao
In this paper, a new parameter perturbation attack on DNNs, called adversarial parameter attack, is proposed, in which small perturbations to the parameters of the DNN are made suc…
Robust and Information-theoretically Safe Bias Classifier against Adversarial Attacks
Lijia Yu, Xiao-Shan Gao
In this paper, the bias classifier is introduced, that is, the bias part of a DNN with Relu as the activation function is used as a classifier. The work is motivated by the fact th…
A Robust Classification-autoencoder to Defend Outliers and Adversaries
Lijia Yu, Xiao-Shan Gao
In this paper, a robust classification-autoencoder (CAE) is proposed, which has strong ability to recognize outliers and defend adversaries. The main idea is to change the autoenco…
Improve the Robustness and Accuracy of Deep Neural Network with Normalization
Lijia Yu, Xiao-Shan Gao
In this paper, the robustness and accuracy of the deep neural network (DNN) was enhanced by introducing the normalization of the weight matrices of the DNN with Relu…