Search Results for author:
Found 5 papers, 1 papers with code
It's Simplex! Disaggregating Measures to Improve Certified Robustness
Certified robustness circumvents the fragility of defences against adversarial attacks, by endowing model predictions with guarantees of class invariance for attacks up to a calculated size.
Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks
Poisoning attacks can disproportionately influence model behaviour by making small changes to the training corpus.
Failure-tolerant Distributed Learning for Anomaly Detection in Wireless Networks
When such failures arise in wireless communications networks, important services that they use/provide (like anomaly detection) can be left inoperable and can result in a cascade of security problems.
Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
In guaranteeing the absence of adversarial examples in an instance's neighbourhood, certification mechanisms play an important role in demonstrating neural net robustness.
Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity
In response to subtle adversarial examples flipping classifications of neural network models, recent research has promoted certified robustness as a solution.
