Search Results for author:
Found 8 papers, 3 papers with code
Verifiable Boosted Tree Ensembles
Verifiable learning advocates for training machine learning models amenable to efficient security verification.
Verifiable Learning for Robust Tree Ensembles
In this paper, we identify a restricted class of decision tree ensembles, called large-spread ensembles, which admit a security verification algorithm running in polynomial time.
Explainable Global Fairness Verification of Tree-Based Classifiers
We present a new approach to the global fairness verification of tree-based classifiers.
Beyond Robustness: Resilience Verification of Tree-Based Classifiers
In this paper we criticize the robustness measure traditionally employed to assess the performance of machine learning models deployed in adversarial settings.
Can I Take Your Subdomain? Exploring Related-Domain Attacks in the Modern Web
Related-domain attackers control a sibling domain of their target web application, e. g., as the result of a subdomain takeover.
Cryptography and Security
Certifying Decision Trees Against Evasion Attacks by Program Analysis
Machine learning has proved invaluable for a range of different tasks, yet it also proved vulnerable to evasion attacks, i. e., maliciously crafted perturbations of input data designed to force mispredictions.
Feature Partitioning for Robust Tree Ensembles and their Certification in Adversarial Scenarios
The attacker aims at finding a minimal perturbation of a test instance that changes the model outcome.
Treant: Training Evasion-Aware Decision Trees
Despite its success and popularity, machine learning is now recognized as vulnerable to evasion attacks, i. e., carefully crafted perturbations of test inputs designed to force prediction errors.
