13 citations · 21 across the 11 of their papers we have counts for
15 papers
Watermarking Decision Tree Ensembles
Stefano Calzavara, Lorenzo Cazzaro, Donald Gera +1
Protecting the intellectual property of machine learning models is a hot topic and many watermarking schemes for deep neural networks have been proposed in the literature. Unfortun…
Timber! Poisoning Decision Trees
Stefano Calzavara, Lorenzo Cazzaro, Massimo Vettori
We present Timber, the first white-box poisoning attack targeting decision trees. Timber is based on a greedy attack strategy that leverages sub-tree retraining to efficiently esti…
Verifiable Boosted Tree Ensembles
Stefano Calzavara, Lorenzo Cazzaro, Claudio Lucchese +1
Verifiable learning advocates for training machine learning models amenable to efficient security verification. Prior research demonstrated that specific classes of decision tree e…
Verifiable Learning for Robust Tree Ensembles
Stefano Calzavara, Lorenzo Cazzaro, Giulio Ermanno Pibiri +1
Verifying the robustness of machine learning models against evasion attacks at test time is an important research problem. Unfortunately, prior work established that this problem i…
Explainable Global Fairness Verification of Tree-Based Classifiers
Stefano Calzavara, Lorenzo Cazzaro, Claudio Lucchese +1
We present a new approach to the global fairness verification of tree-based classifiers. Given a tree-based classifier and a set of sensitive features potentially leading to discri…
Beyond Robustness: Resilience Verification of Tree-Based Classifiers
Stefano Calzavara, Lorenzo Cazzaro, Claudio Lucchese +2
In this paper we criticize the robustness measure traditionally employed to assess the performance of machine learning models deployed in adversarial settings. To mitigate the limi…
Bulwark: Holistic and Verified Security Monitoring of Web Protocols
Lorenzo Veronese, Stefano Calzavara, Luca Compagna
Modern web applications often rely on third-party services to provide their functionality to users. The secure integration of these services is a non-trivial task, as shown by the…
Can I Take Your Subdomain? Exploring Related-Domain Attacks in the Modern Web
Marco Squarcina, Mauro Tempesta, Lorenzo Veronese +2
Related-domain attackers control a sibling domain of their target web application, e.g., as the result of a subdomain takeover. Despite their additional power over traditional web…
Certifying Decision Trees Against Evasion Attacks by Program Analysis
Stefano Calzavara, Pietro Ferrara, Claudio Lucchese
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 desig…
Feature Partitioning for Robust Tree Ensembles and their Certification in Adversarial Scenarios
Stefano Calzavara, Claudio Lucchese, Federico Marcuzzi +1
Machine learning algorithms, however effective, are known to be vulnerable in adversarial scenarios where a malicious user may inject manipulated instances. In this work we focus o…
Language-Based Web Session Integrity
Stefano Calzavara, Riccardo Focardi, Niklas Grimm +2
Session management is a fundamental component of web applications: despite the apparent simplicity, correctly implementing web sessions is extremely tricky, as witnessed by the lar…
Treant: Training Evasion-Aware Decision Trees
Stefano Calzavara, Claudio Lucchese, Gabriele Tolomei +2
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 pred…
WPSE: Fortifying Web Protocols via Browser-Side Security Monitoring
Stefano Calzavara, Riccardo Focardi, Matteo Maffei +3
We present WPSE, a browser-side security monitor for web protocols designed to ensure compliance with the intended protocol flow, as well as confidentiality and integrity propertie…
HornDroid: Practical and Sound Static Analysis of Android Applications by SMT Solving
Stefano Calzavara, Ilya Grishchenko, Matteo Maffei
We present HornDroid, a new tool for the static analysis of information flow properties in Android applications. The core idea underlying HornDroid is to use Horn clauses for sound…
A Sound Flow-Sensitive Heap Abstraction for the Static Analysis of Android Applications
Stefano Calzavara, Ilya Grishchenko, Adrien Koutsos +1
The present paper proposes the first static analysis for Android applications which is both flow-sensitive on the heap abstraction and provably sound with respect to a rich formal…