Competitions with currently unpublished results:

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

# An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacks

According to the recent studies, the vulnerability of state of the art Neural Networks to adversarial input samples has increased drastically.

0
29 Apr 2021

# Fast Certified Robust Training via Better Initialization and Shorter Warmup

31 Mar 2021shizhouxing/Fast-Certified-Robust-Training

Despite state-of-the-art (SOTA) methods including interval bound propagation (IBP) and CROWN-IBP have per-batch training complexity similar to standard neural network training, to reach SOTA performance they usually need a long warmup schedule with hundreds or thousands epochs and are thus still quite costly for training.

5
31 Mar 2021

# LiBRe: A Practical Bayesian Approach to Adversarial Detection

27 Mar 2021thudzj/ScalableBDL

Despite their appealing flexibility, deep neural networks (DNNs) are vulnerable against adversarial examples.

10
27 Mar 2021

# Sandwich Batch Normalization

22 Feb 2021VITA-Group/Sandwich-Batch-Normalization

We present Sandwich Batch Normalization (SaBN), an embarrassingly easy improvement of Batch Normalization (BN) with only a few lines of code changes.

32
22 Feb 2021

# A Person Re-identification Data Augmentation Method with Adversarial Defense Effect

21 Jan 2021finger-monkey/Data-Augmentation

This method can not only improve the accuracy of the model, but also help the model defend against adversarial examples; 2) Multi-Modal Defense, it integrates three homogeneous modal images of visible, grayscale and sketch, and further strengthens the defense ability of the model.

9
21 Jan 2021

# Defending against black-box adversarial attacks with gradient-free trained sign activation neural networks

1 Jan 2021zero-one-loss/scd_github

The non-transferability in our ensemble also makes it a powerful defense to substitute model black box attacks that we show require a much greater distortion than binary and full precision networks to bring our model to zero adversarial accuracy.

0
01 Jan 2021

# Geometric Adversarial Attacks and Defenses on 3D Point Clouds

Deep neural networks are prone to adversarial examples that maliciously alter the network's outcome.

14
10 Dec 2020

Further, we propose Guided Adversarial Training (GAT), which achieves state-of-the-art performance amongst single-step defenses by utilizing the proposed relaxation term for both attack generation and training.

7
30 Nov 2020

# Learnable Boundary Guided Adversarial Training

23 Nov 2020FPNAS/LBGAT

We use the model logits from one clean model $\mathcal{M}^{natural}$ to guide learning of the robust model $\mathcal{M}^{robust}$, taking into consideration that logits from the well trained clean model $\mathcal{M}^{natural}$ embed the most discriminative features of natural data, {\it e. g.}, generalizable classifier boundary.

3
23 Nov 2020

# Information Obfuscation of Graph Neural Networks

28 Sep 2020liaopeiyuan/GAL

While the advent of Graph Neural Networks (GNNs) has greatly improved node and graph representation learning in many applications, the neighborhood aggregation scheme exposes additional vulnerabilities to adversaries seeking to extract node-level information about sensitive attributes.

22
28 Sep 2020