Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

Li, Muyang; Lin, Ji; Meng, Chenlin; Ermon, Stefano; Han, Song; Zhu, Jun-Yan

doi:10.1109/tpami.2023.3316020

Cited by 3 publications

(1 citation statement)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gulrajani and Ahmed [25] anticipated an enhanced WGAN algorithm that penalizes the norm of discriminator gradients to train the discriminator network with respect to the sample data. There are several structure GAN algorithms including fully connected GANs [26], Conditional GANs [27], Convolutional GANs [28], GANs with inference models [27], and adversarial autoencoders [29]. Most of these algorithms use the standard loss function which suffers from the vanishing gradient problem and, thus, leads to instability and model collabs especially when insufficient data is used for training the classification task.…”

Section: Related Workmentioning

confidence: 99%

An Enhanced Minimax Loss Function Technique in Generative Adversarial Network for Ransomware Behavior Prediction

Gazzan,

Sheldon

2023

Future Internet

View full text Add to dashboard Cite

Recent ransomware attacks threaten not only personal files but also critical infrastructure like smart grids, necessitating early detection before encryption occurs. Current methods, reliant on pre-encryption data, suffer from insufficient and rapidly outdated attack patterns, despite efforts to focus on select features. Such an approach assumes that the same features remain unchanged. This approach proves ineffective due to the polymorphic and metamorphic characteristics of ransomware, which generate unique attack patterns for each new target, particularly in the pre-encryption phase where evasiveness is prioritized. As a result, the selected features quickly become obsolete. Therefore, this study proposes an enhanced Bi-Gradual Minimax (BGM) loss function for the Generative Adversarial Network (GAN) Algorithm that compensates for the attack patterns insufficiency to represents the polymorphic behavior at the earlier phases of the ransomware lifecycle. Unlike existing GAN-based models, the BGM-GAN gradually minimizes the maximum loss of the generator and discriminator in the network. This allows the generator to create artificial patterns that resemble the pre-encryption data distribution. The generator is used to craft evasive adversarial patterns and add them to the original data. Then, the generator and discriminator compete to optimize their weights during the training phase such that the generator produces realistic attack patterns, while the discriminator endeavors to distinguish between the real and crafted patterns. The experimental results show that the proposed BGM-GAN reached maximum accuracy of 0.98, recall (0.96), and a minimum false positive rate (0.14) which all outperform those obtained by the existing works. The application of BGM-GAN can be extended to early detect malware and other types of attacks.

show abstract