62 citations · 85 across the 14 of their papers we have counts for
14 papers
Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks
Ziqiang Li, Yueqi Zeng, Pengfei Xia +3
With the burgeoning advancements in the field of natural language processing (NLP), the demand for training data has increased significantly. To save costs, it has become common fo…
Efficient Trigger Word Insertion
Yueqi Zeng, Ziqiang Li, Pengfei Xia +2
With the boom in the natural language processing (NLP) field these years, backdoor attacks pose immense threats against deep neural network models. However, previous works hardly c…
Explore the Effect of Data Selection on Poison Efficiency in Backdoor Attacks
Ziqiang Li, Pengfei Xia, Hong Sun +3
As the number of parameters in Deep Neural Networks (DNNs) scales, the thirst for training data also increases. To save costs, it has become common for users and enterprises to del…
Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
Ziqiang Li, Hong Sun, Pengfei Xia +4
Recent deep neural networks (DNNs) have came to rely on vast amounts of training data, providing an opportunity for malicious attackers to exploit and contaminate the data to carry…
A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
Ziqiang Li, Hong Sun, Pengfei Xia +6
Poisoning efficiency is crucial in poisoning-based backdoor attacks, as attackers aim to minimize the number of poisoning samples while maximizing attack efficacy. Recent studies h…
Frequency Decomposition to Tap the Potential of Single Domain for Generalization
Qingyue Yang, Hongjing Niu, Pengfei Xia +2
Domain generalization (DG), aiming at models able to work on multiple unseen domains, is a must-have characteristic of general artificial intelligence. DG based on single source do…
Data-Efficient Backdoor Attacks
Pengfei Xia, Ziqiang Li, Wei Zhang +1
Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behav…
Enhancing Backdoor Attacks with Multi-Level MMD Regularization
Pengfei Xia, Hongjing Niu, Ziqiang Li +1
While Deep Neural Networks (DNNs) excel in many tasks, the huge training resources they require become an obstacle for practitioners to develop their own models. It has become comm…
Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search
Pengfei Xia, Ziqiang Li, Bin Li
Despite achieving great success, Deep Neural Networks (DNNs) are vulnerable to adversarial examples. How to accurately evaluate the adversarial robustness of DNNs is critical for t…
Exploring The Effect of High-frequency Components in GANs Training
Ziqiang Li, Pengfei Xia, Xue Rui +1
Generative Adversarial Networks (GANs) have the ability to generate images that are visually indistinguishable from real images. However, recent studies have revealed that generate…
Understanding the Error in Evaluating Adversarial Robustness
Pengfei Xia, Ziqiang Li, Hongjing Niu +1
Deep neural networks are easily misled by adversarial examples. Although lots of defense methods are proposed, many of them are demonstrated to lose effectiveness when against prop…
Improving Resistance to Adversarial Deformations by Regularizing Gradients
Pengfei Xia, Bin Li
Improving the resistance of deep neural networks against adversarial attacks is important for deploying models to realistic applications. However, most defense methods are designed…
A New Perspective on Stabilizing GANs training: Direct Adversarial Training
Ziqiang Li, Pengfei Xia, Rentuo Tao +2
Generative Adversarial Networks (GANs) are the most popular image generation models that have achieved remarkable progress on various computer vision tasks. However, training insta…
A Systematic Survey of Regularization and Normalization in GANs
Ziqiang Li, Muhammad Usman, Rentuo Tao +4
Generative Adversarial Networks (GANs) have been widely applied in different scenarios thanks to the development of deep neural networks. The original GAN was proposed based on the…