v1v2 (latest)

The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks from Concentration of Measure

9 September 2018

Saeed Mahloujifar

Dimitrios I. Diochnos

Mohammad Mahmoody

ArXiv (abs)PDF HTML

Papers citing "The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks from Concentration of Measure"

50 / 58 papers shown

Title
$Existence of Adversarial Examples for Random Convolutional Networks via Isoperimetric Inequalities on $\mathbb{so}(d)$$ Existence of Adversarial Examples for Random Convolutional Networks via Isoperimetric Inequalities on $\mathbb{so}(d)$ Amit Daniely 23 0 0 14 Jun 2025
Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness Ambar Pal Huaijin Hao Rene Vidal 100 8 0 28 Sep 2023
Linking convolutional kernel size to generalization bias in face analysis CNNs Hao Liang J. O. Caro Vikram Maheshri Ankit B. Patel Guha Balakrishnan CVBM CML 68 0 0 07 Feb 2023
Enhancing Quantum Adversarial Robustness by Randomized Encodings Weiyuan Gong D. Yuan Weikang Li D. Deng AAML 105 19 0 05 Dec 2022
When are Local Queries Useful for Robust Learning? Pascale Gourdeau Varun Kanade Marta Z. Kwiatkowska J. Worrell OOD 86 1 0 12 Oct 2022
Lethal Dose Conjecture on Data Poisoning Wenxiao Wang Alexander Levine Soheil Feizi FedML 53 15 0 05 Aug 2022
Sample Complexity Bounds for Robustly Learning Decision Lists against Evasion Attacks Pascale Gourdeau Varun Kanade Marta Z. Kwiatkowska J. Worrell AAML 55 5 0 12 May 2022
On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes Elvis Dohmatob A. Bietti AAML 85 13 0 22 Mar 2022
Adversarial robustness of sparse local Lipschitz predictors Ramchandran Muthukumar Jeremias Sulam AAML 92 13 0 26 Feb 2022
The Many Faces of Adversarial Risk Muni Sreenivas Pydi Varun Jog AAML 71 30 0 22 Jan 2022
Image classifiers can not be made robust to small perturbations Zheng Dai David K Gifford VLM AAML 74 1 0 07 Dec 2021
Classification and Adversarial examples in an Overparameterized Linear Model: A Signal Processing Perspective Adhyyan Narang Vidya Muthukumar A. Sahai SILM AAML 69 1 0 27 Sep 2021
Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive Features Hui Liu Bo Zhao Minzhi Ji Yuefeng Peng Jiabao Guo Peng Liu AAML 63 2 0 19 Jul 2021
The Dimpled Manifold Model of Adversarial Examples in Machine Learning A. Shamir Odelia Melamed Oriel BenShmuel AAML 96 50 0 18 Jun 2021
Learning and Certification under Instance-targeted Poisoning Ji Gao Amin Karbasi Mohammad Mahmoody AAML 62 15 0 18 May 2021
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness? Vikash Sehwag Saeed Mahloujifar Tinashe Handina Sihui Dai Chong Xiang M. Chiang Prateek Mittal OOD 102 131 0 19 Apr 2021
Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries A. Bhagoji Daniel Cullina Vikash Sehwag Prateek Mittal AAML OOD 73 3 0 16 Apr 2021
Trusted Artificial Intelligence: Towards Certification of Machine Learning Applications P. M. Winter Sebastian K. Eder J. Weissenbock Christoph Schwald Thomas Doms Tom Vogt Sepp Hochreiter Bernhard Nessler 111 25 0 31 Mar 2021
$Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half Spaces$ Improved Estimation of Concentration Under $\ell_p$ -Norm Distance Metrics Using Half Spaces Jack Prescott Xiao Zhang David Evans 49 5 0 24 Mar 2021
Universal Adversarial Examples and Perturbations for Quantum Classifiers Weiyuan Gong D. Deng AAML 88 25 0 15 Feb 2021
Property Inference From Poisoning Melissa Chase Esha Ghosh Saeed Mahloujifar MIACV 90 83 0 26 Jan 2021
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses Micah Goldblum Dimitris Tsipras Chulin Xie Xinyun Chen Avi Schwarzschild Basel Alomair Aleksander Madry Yue Liu Tom Goldstein SILM 129 282 0 18 Dec 2020
Adversarial Classification: Necessary conditions and geometric flows Nicolas García Trillos Ryan W. Murray AAML 93 19 0 21 Nov 2020
Adversarial Robust Training of Deep Learning MRI Reconstruction Models Francesco Calivá Kaiyang Cheng Rutwik Shah V. Pedoia OOD AAML MedIm 84 11 0 30 Oct 2020
Adversarial Concept Drift Detection under Poisoning Attacks for Robust Data Stream Mining Lukasz Korycki Bartosz Krawczyk AAML 120 23 0 20 Sep 2020
Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspective G. R. Machado Eugênio Silva R. Goldschmidt AAML 136 162 0 08 Sep 2020
Learning from Noisy Labels with Deep Neural Networks: A Survey Hwanjun Song Minseok Kim Dongmin Park Yooju Shin Jae-Gil Lee NoLa 136 1,005 0 16 Jul 2020
Understanding Adversarial Examples from the Mutual Influence of Images and Perturbations Chaoning Zhang Philipp Benz Tooba Imtiaz In-So Kweon SSL AAML 83 119 0 13 Jul 2020
Host-Pathongen Co-evolution Inspired Algorithm Enables Robust GAN Training Andrei Kucharavy El-Mahdi El-Mhamdi R. Guerraoui GAN 45 1 0 22 May 2020
Feature Purification: How Adversarial Training Performs Robust Deep Learning Zeyuan Allen-Zhu Yuanzhi Li MLT AAML 122 151 0 20 May 2020
Certifying Joint Adversarial Robustness for Model Ensembles M. Jonas David Evans AAML 60 2 0 21 Apr 2020
Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models Xiao Zhang Jinghui Chen Quanquan Gu David Evans 76 17 0 01 Mar 2020
Utilizing Network Properties to Detect Erroneous Inputs Matt Gorbett Nathaniel Blanchard AAML 61 6 0 28 Feb 2020
Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization Sicheng Zhu Xiao Zhang David Evans SSL OOD 93 27 0 26 Feb 2020
Precise Tradeoffs in Adversarial Training for Linear Regression Adel Javanmard Mahdi Soltanolkotabi Hamed Hassani AAML 80 109 0 24 Feb 2020
More Data Can Expand the Generalization Gap Between Adversarially Robust and Standard Models Lin Chen Yifei Min Mingrui Zhang Amin Karbasi OOD 84 64 0 11 Feb 2020
Local intrinsic dimensionality estimators based on concentration of measure Jonathan Bac A. Zinovyev 49 10 0 31 Jan 2020
Adversarial Risk via Optimal Transport and Optimal Couplings Muni Sreenivas Pydi Varun Jog 85 60 0 05 Dec 2019
Label-Consistent Backdoor Attacks Alexander Turner Dimitris Tsipras Aleksander Madry AAML 97 391 0 05 Dec 2019
On Robustness to Adversarial Examples and Polynomial Optimization Pranjal Awasthi Abhratanu Dutta Aravindan Vijayaraghavan OOD AAML 78 32 0 12 Nov 2019
Instance adaptive adversarial training: Improved accuracy tradeoffs in neural nets Yogesh Balaji Tom Goldstein Judy Hoffman AAML 205 103 0 17 Oct 2019
Lower Bounds on Adversarial Robustness from Optimal Transport A. Bhagoji Daniel Cullina Prateek Mittal OOD OT AAML 70 94 0 26 Sep 2019
On the Hardness of Robust Classification Pascale Gourdeau Varun Kanade Marta Z. Kwiatkowska J. Worrell 74 44 0 12 Sep 2019
Computational Concentration of Measure: Optimal Bounds, Reductions, and More O. Etesami Saeed Mahloujifar Mohammad Mahmoody 44 16 0 11 Jul 2019
Quantitative Verification of Neural Networks And its Security Applications Teodora Baluta Shiqi Shen Shweta Shinde Kuldeep S. Meel P. Saxena AAML 89 105 0 25 Jun 2019
Lower Bounds for Adversarially Robust PAC Learning Dimitrios I. Diochnos Saeed Mahloujifar Mohammad Mahmoody AAML 80 26 0 13 Jun 2019
Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness Saeed Mahloujifar Xiao Zhang Mohammad Mahmoody David Evans 64 22 0 29 May 2019
High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks Haohan Wang Xindi Wu Pengcheng Yin Eric Xing 79 526 0 28 May 2019
Adversarially Robust Learning Could Leverage Computational Hardness Sanjam Garg S. Jha Saeed Mahloujifar Mohammad Mahmoody AAML 163 24 0 28 May 2019
Adversarial Examples Are Not Bugs, They Are Features Andrew Ilyas Shibani Santurkar Dimitris Tsipras Logan Engstrom Brandon Tran Aleksander Madry SILM 104 1,846 0 06 May 2019