Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Emil C. Lupu

Regularization Can Help Mitigate Poisoning Attacks... with the Right Hyperparameters


May 23, 2021
Javier Carnerero-Cano, Luis Muñoz-González, Phillippa Spencer, Emil C. Lupu

* Published at ICLR 2021 Workshop on Security and Safety in Machine Learning Systems. arXiv admin note: text overlap with arXiv:2003.00040 

  Access Paper or Ask Questions

Real-time Detection of Practical Universal Adversarial Perturbations


May 22, 2021
Kenneth T. Co, Luis Muñoz-González, Leslie Kanthan, Emil C. Lupu


  Access Paper or Ask Questions

Jacobian Regularization for Mitigating Universal Adversarial Perturbations


Apr 21, 2021
Kenneth T. Co, David Martinez Rego, Emil C. Lupu


  Access Paper or Ask Questions

Object Removal Attacks on LiDAR-based 3D Object Detectors


Feb 07, 2021
Zhongyuan Hau, Kenneth T. Co, Soteris Demetriou, Emil C. Lupu

* Accepted to AutoSec at NDSS 2021 

  Access Paper or Ask Questions

Robustness and Transferability of Universal Attacks on Compressed Models


Dec 10, 2020
Alberto G. Matachana, Kenneth T. Co, Luis Muñoz-González, David Martinez, Emil C. Lupu

* Accepted to AAAI 2021 Workshop: Towards Robust, Secure and Efficient Machine Learning 

  Access Paper or Ask Questions

Regularisation Can Mitigate Poisoning Attacks: A Novel Analysis Based on Multiobjective Bilevel Optimisation


Feb 28, 2020
Javier Carnerero-Cano, Luis Muñoz-González, Phillippa Spencer, Emil C. Lupu


  Access Paper or Ask Questions

Universal Adversarial Perturbations to Understand Robustness of Texture vs. Shape-biased Training


Nov 23, 2019
Kenneth T. Co, Luis Muñoz-González, Leslie Kanthan, Ben Glocker, Emil C. Lupu

* 9 pages, 6 figures 

  Access Paper or Ask Questions

Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging


Sep 11, 2019
Luis Muñoz-González, Kenneth T. Co, Emil C. Lupu


  Access Paper or Ask Questions

Poisoning Attacks with Generative Adversarial Nets


Jun 18, 2019
Luis Muñoz-González, Bjarne Pfitzner, Matteo Russo, Javier Carnerero-Cano, Emil C. Lupu


  Access Paper or Ask Questions

Sensitivity of Deep Convolutional Networks to Gabor Noise


Jun 11, 2019
Kenneth T. Co, Luis Muñoz-González, Emil C. Lupu

* Accepted to ICML 2019 Workshop on Identifying and Understanding Deep Learning Phenomena 

  Access Paper or Ask Questions

An Argumentation-Based Approach to Assist in the Investigation and Attribution of Cyber-Attacks


Apr 30, 2019
Erisa Karafili, Linna Wang, Emil C. Lupu


  Access Paper or Ask Questions

Label Sanitization against Label Flipping Poisoning Attacks


Oct 02, 2018
Andrea Paudice, Luis Muñoz-González, Emil C. Lupu


  Access Paper or Ask Questions

Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Neural Networks


Sep 30, 2018
Kenneth T. Co, Luis Muñoz-González, Emil C. Lupu

* 15 pages 

  Access Paper or Ask Questions

Mitigation of Adversarial Attacks through Embedded Feature Selection


Aug 16, 2018
Ziyi Bao, Luis Muñoz-González, Emil C. Lupu


  Access Paper or Ask Questions

Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection


Feb 08, 2018
Andrea Paudice, Luis Muñoz-González, Andras Gyorgy, Emil C. Lupu

* 10 pages, 3 figures 

  Access Paper or Ask Questions

Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization


Aug 29, 2017
Luis Muñoz-González, Battista Biggio, Ambra Demontis, Andrea Paudice, Vasin Wongrassamee, Emil C. Lupu, Fabio Roli


  Access Paper or Ask Questions

Argumentation-based Security for Social Good


May 01, 2017
Erisa Karafili, Antonis C. Kakas, Nikolaos I. Spanoudakis, Emil C. Lupu

* Paper presented at the AAAI Spring Symposium 2017, 7 pages 

  Access Paper or Ask Questions

Efficient Attack Graph Analysis through Approximate Inference


Jun 22, 2016
Luis Muñoz-González, Daniele Sgandurra, Andrea Paudice, Emil C. Lupu

* 30 pages, 14 figures 

  Access Paper or Ask Questions