Search Results for author: Chris Hankin

Found 4 papers, 0 papers with code

Certified Federated Adversarial Training

no code implementations20 Dec 2021 Giulio Zizzo, Ambrish Rawat, Mathieu Sinn, Sergio Maffeis, Chris Hankin

We model an attacker who poisons the model to insert a weakness into the adversarial training such that the model displays apparent adversarial robustness, while the attacker can exploit the inserted weakness to bypass the adversarial training and force the model to misclassify adversarial examples.

Adversarial Robustness Federated Learning

Fault Tree Analysis: Identifying Maximum Probability Minimal Cut Sets with MaxSAT

no code implementations5 May 2020 Martín Barrère, Chris Hankin

In this paper, we present a novel MaxSAT-based technique to compute Maximum Probability Minimal Cut Sets (MPMCSs) in fault trees.

Adversarial Attacks on Time-Series Intrusion Detection for Industrial Control Systems

no code implementations8 Nov 2019 Giulio Zizzo, Chris Hankin, Sergio Maffeis, Kevin Jones

In the continuous data domain our attack successfully hides the cyber-physical attacks requiring 2. 87 out of 12 monitored sensors to be compromised on average.

Adversarial Attack Intrusion Detection +2

Deep Latent Defence

no code implementations9 Oct 2019 Giulio Zizzo, Chris Hankin, Sergio Maffeis, Kevin Jones

The level of perturbation an attacker needs to introduce in order to cause such a misclassification can be extremely small, and often imperceptible.

Cannot find the paper you are looking for? You can Submit a new open access paper.