CNOCycle

1. fix for data type 2. set training=False 3. fix for gradient issue #1087

The implementation of resnet may not correct.

1

The original resnet [papaer](https://arxiv.org/pdf/1512.03385.pdf) summaries each layer's output size in Table 1. The output size of last conv5_x layer (before avg_pool) is `7x7`. But `ResNet` from `keras-contrib` is `4x4`. The...

Hi author, I'm developing a robust model. For some mathematical reasons, input images should be defined in range [0, 1]. However, attacks are implemented by tanh which range is [-0.5,...

Added support for Overload attack

2

# Description This pull request adds the support of the Overload Attack proposed in [1]. [1] Overload: Latency Attacks on Object Detection for Edge Devices. [[Paper]](https://arxiv.org/abs/2304.05370) ## Type of change...

[New Model] Chen2024Data

4

# Paper Information - **Paper Title**: Data filtering for efficient adversarial training - **Paper URL**: https://doi.org/10.1016/j.patcog.2024.110394 - **Paper authors**: Erh-Chung Chen, Che-Rung Lee # Leaderboard Claim(s) ## Model 1 -...

Support Transpose op in TFlite

16

### Pull Request Readiness Checklist **Merge with extra**: https://github.com/opencv/opencv_extra/pull/1168 The purpose of this PR is to introduce support for the Transpose op in TFlite format and to add a shape...

Added support for SNAL attack

1

# Description This pull request adds the support of the SNAL Attack proposed in [1]. [1]Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks. [[Paper]](https://arxiv.org/abs/2404.15881)...