7 citations · 17 across the 6 of their papers we have counts for
6 papers
UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA
Rachneet Sachdeva, Haritz Puerto, Tim Baumgärtner +6
Question Answering (QA) systems are increasingly deployed in applications where they support real-world decisions. However, state-of-the-art models rely on deep neural networks, wh…
Wavelet Regularization Benefits Adversarial Training
Jun Yan, Huilin Yin, Xiaoyang Deng +4
Adversarial training methods are state-of-the-art (SOTA) empirical defense methods against adversarial examples. Many regularization methods have been proven to be effective with t…
Why Adversarial Training of ReLU Networks Is Difficult?
Xu Cheng, Hao Zhang, Yue Xin +3
This paper mathematically derives an analytic solution of the adversarial perturbation on a ReLU network, and theoretically explains the difficulty of adversarial training. Specifi…
Towards a Unified Evaluation of Explanation Methods without Ground Truth
Hao Zhang, Jiayi Chen, Haotian Xue +1
This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also p…
Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding
Haotian Ma, Hao Zhang, Fan Zhou +2
This paper presents a method to explain how the information of each input variable is gradually discarded during the forward propagation in a deep neural network (DNN), which provi…
Interpretable Complex-Valued Neural Networks for Privacy Protection
Liyao Xiang, Haotian Ma, Hao Zhang +3
Previous studies have found that an adversary attacker can often infer unintended input information from intermediate-layer features. We study the possibility of preventing such ad…