Search Results for author:
Found 12 papers, 7 papers with code
Efficient Trigger Word Insertion
With the boom in the natural language processing (NLP) field these years, backdoor attacks pose immense threats against deep neural network models.
Explore the Effect of Data Selection on Poison Efficiency in Backdoor Attacks
In this study, we focus on improving the poisoning efficiency of backdoor attacks from the sample selection perspective.
Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
However, existing backdoor attack methods make unrealistic assumptions, assuming that all training data comes from a single source and that attackers have full access to the training data.
A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
This paper presents a Proxy attack-Free Strategy (PFS) designed to identify efficient poisoning samples based on individual similarity and ensemble diversity, effectively addressing the mentioned concern.
Frequency Decomposition to Tap the Potential of Single Domain for Generalization
Then, a new method that learns through multiple frequency domains is proposed.
Data-Efficient Backdoor Attacks
Recent studies have proven that deep neural networks are vulnerable to backdoor attacks.
Enhancing Backdoor Attacks with Multi-Level MMD Regularization
Then, ML-MMDR, a difference reduction method that adds multi-level MMD regularization into the loss, is proposed, and its effectiveness is testified on three typical difference-based defense methods.
Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search
The most common solution for this is to compute an approximate risk by replacing the 0-1 loss with a surrogate one.
Exploring The Effect of High-frequency Components in GANs Training
Generative Adversarial Networks (GANs) have the ability to generate images that are visually indistinguishable from real images.
Improving Resistance to Adversarial Deformations by Regularizing Gradients
Improving the resistance of deep neural networks against adversarial attacks is important for deploying models to realistic applications.
A Systematic Survey of Regularization and Normalization in GANs
Although a handful number of regularization and normalization methods have been proposed for GANs, to the best of our knowledge, there exists no comprehensive survey that primarily focuses on objectives and development of these methods, apart from some in-comprehensive and limited scope studies.
A New Perspective on Stabilizing GANs training: Direct Adversarial Training
Quite a number of methods have been proposed to stabilize the training of GANs, the focuses of which were respectively put on the loss functions, regularization and normalization technologies, training algorithms, and model architectures.
