paper-with-me

홈 › Papers

Is AmI (Attacks Meet Interpretability) Robust to Adversarial Examples?

2019-02-06 · Nicholas Carlini

No.

📄 PDF Abstract BibTeX arXiv:1902.02322

Code (1)

carlini/AmI 공식 구현 tf

Tasks

Adversarial AttackAdversarial Defense

Similar Papers 제목 키워드 기반

Visual Interpretability Alone Helps Adversarial Robustness

2019-09-25 · Akhilan Boopathy, Sijia Liu, Gaoyuan Zhang, Pin-Yu Chen 외

Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability, and interpretability is itself susceptible to adversarial attacks. In this paper, we t…

Adversarial Robustness

Proper Network Interpretability Helps Adversarial Robustness in Classification

2020-06-26 · ICML 2020 1 · Akhilan Boopathy, Sijia Liu, Gaoyuan Zhang, Cynthia Liu 외

Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itse…

Adversarial RobustnessClassificationGeneral ClassificationNetwork Interpretation+1

Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples

2018-10-27 · NeurIPS 2018 12 · Guanhong Tao, Shiqing Ma, Yingqi Liu, Xiangyu Zhang

Adversarial sample attacks perturb benign inputs to induce DNN misbehaviors. Recent research has demonstrated the widespread presence and the devastating consequences of such attacks. Existing defense techniques either a…

AttributeFace RecognitionGeneral Classification

Adversarial Attacks on ASR Systems: An Overview

2022-08-03 · Xiao Zhang, Hao Tan, Xuan Huang, Denghui Zhang 외

With the development of hardware and algorithms, ASR(Automatic Speech Recognition) systems evolve a lot. As The models get simpler, the difficulty of development and deployment become easier, ASR systems are getting clos…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signatures

2019-09-08 · Gil Fidel, Ron Bitton, Asaf Shabtai

State-of-the-art deep neural networks (DNNs) are highly effective in solving many complex real-world problems. However, these models are vulnerable to adversarial perturbation attacks, and despite the plethora of researc…