Hiding Audio in Images: A Deep Learning Approach

Gandikota, Rohit; Mishra, Deepak

doi:10.1007/978-3-030-34872-4_43

Cited by 6 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Between them, we regard the architecture utilizing raw audio data as the baseline. The architecture using STFT, which is applied in [13,16], as a method to improve the baseline.…”

Section: Performance Experimentsmentioning

confidence: 99%

“…For instance, Huu et al [16] achieve embedding a 4 second audio clip with short-time fourier transform (STFT) format in a 255×255 image by using deep convolutional neural network (DCNN) model. Gandikota et al [13] utilize the generative adversarial networks (GAN) model to hide a 2 second audio clip in a 128×128 image. It is clear that the length of concealed au-dio in the aforementioned works are not enough.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Materials chemistry at Nankai University: A special issue dedicated to the 100th anniversary of Nankai University

Zhao

et al. 2019

Sci. China Mater.

View full text Add to dashboard Cite

Proactive failure detection of instances is vitally essential to microservice systems because an instance failure can propagate to the whole system and degrade the system's performance. Over the years, many single-modal (i.e., metrics, logs, or traces) data-based anomaly detection methods have been proposed. However, they tend to miss a large number of failures and generate numerous false alarms because they ignore the correlation of multimodal data. In this work, we propose AnoFusion, an unsupervised failure detection approach, to proactively detect instance failures through multimodal data for microservice systems. It applies a Graph Transformer Network (GTN) to learn the correlation of the heterogeneous multimodal data and integrates a Graph Attention Network (GAT) with Gated Recurrent Unit (GRU) to address the challenges introduced by dynamically changing multimodal data. We evaluate the performance of AnoFusion through two datasets, demonstrating that it achieves the 𝐹 1 -score of 0.857 and 0.922, respectively, outperforming the state-of-the-art failure detection approaches. CCS CONCEPTS• Software and its engineering → Maintaining software; • Computing methodologies → Failure Detection; Graph Neural Networks.

show abstract

“…Between them, we regard the architecture utilizing raw audio data as the baseline. The architecture using STFT, which is applied in [13,16], as a method to improve the baseline.…”

Section: Performance Experimentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%