148 citations · 249 across the 20 of their papers we have counts for
24 papers
Trustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logistics
Antonio Emanuele Cinà, Giovanni Scodeller, Cecilia Caterina Pasquale +5
The rapid evolution of Intelligent Transportation Systems and Logistics (ITS\&L) has become a cornerstone of the modern social economy, relying heavily on the integration of Data,…
Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering
Maria Rosaria Briglia, Igor Maljkovic, Antonio Emanuele Cinà +3
Vision--Language Models (VLMs) are increasingly deployed through a model supply chain in which pretrained checkpoints, architecture definitions, text encoders, and exported computa…
Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization
Igor Maljkovic, Maria Rosaria Briglia, Iacopo Masi +2
Vision-Language Models (VLMs) have become essential for tasks such as image synthesis, captioning, and retrieval by aligning textual and visual information in a shared embedding sp…
Evaluating the Evaluators: Trust in Adversarial Robustness Tests
Antonio Emanuele Cinà, Maura Pintor, Luca Demetrio +3
Despite significant progress in designing powerful adversarial evasion attacks for robustness verification, the evaluation of these methods often remains inconsistent and unreliabl…
Rethinking Robustness in Machine Learning: A Posterior Agreement Approach
João Borges S. Carvalho, Victor Jimenez Rodriguez, Alessandro Torcinovich +4
The robustness of algorithms against covariate shifts is a fundamental problem with critical implications for the deployment of machine learning algorithms in the real world. Curre…
Pirates of Charity: Exploring Donation-based Abuses in Social Media Platforms
Bhupendra Acharya, Dario Lazzaro, Antonio Emanuele Cinà +1
With the widespread use of social media, organizations, and individuals use these platforms to raise funds and support causes. Unfortunately, this has led to the rise of scammers i…
Robust image classification with multi-modal large language models
Francesco Villani, Igor Maljkovic, Dario Lazzaro +3
Deep Neural Networks are vulnerable to adversarial examples, i.e., carefully crafted input samples that can cause models to make incorrect predictions with high confidence. To miti…
On the Robustness of Adversarial Training Against Uncertainty Attacks
Emanuele Ledda, Giovanni Scodeller, Daniele Angioni +5
In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of i…
Sonic: Fast and Transferable Data Poisoning on Clustering Algorithms
Francesco Villani, Dario Lazzaro, Antonio Emanuele Cinà +3
Data poisoning attacks on clustering algorithms have received limited attention, with existing methods struggling to scale efficiently as dataset sizes and feature counts increase.…
Understanding XAI Through the Philosopher's Lens: A Historical Perspective
Martina Mattioli, Antonio Emanuele Cinà, Marcello Pelillo
Despite explainable AI (XAI) has recently become a hot topic and several different approaches have been developed, there is still a widespread belief that it lacks a convincing uni…
Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis
Srishti Gupta, Zhang Chen, Luca Demetrio +9
Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization. However, having a large parameter space is consi…
AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples
Antonio Emanuele Cinà, Jérôme Rony, Maura Pintor +5
Adversarial examples are typically optimized with gradient-based attacks. While novel attacks are continuously proposed, each is shown to outperform its predecessors using differen…
-zero: Gradient-based Optimization of -norm Adversarial Examples
Antonio Emanuele Cinà, Francesco Villani, Maura Pintor +3
Evaluating the adversarial robustness of deep networks to gradient-based attacks is challenging. While most attacks consider - and -norm constraints to craft i…
Conning the Crypto Conman: End-to-End Analysis of Cryptocurrency-based Technical Support Scams
Bhupendra Acharya, Muhammad Saad, Antonio Emanuele Cinà +5
The mainstream adoption of cryptocurrencies has led to a surge in wallet-related issues reported by ordinary users on social media platforms. In parallel, there is an increase in a…
Vector Flows and the Capacity of a Discrete Memoryless Channel
G. Beretta, G. Chiarot, A. E. Cinà +1
One of the fundamental problems of information theory, since its foundation by Shannon in 1948, has been the computation of the capacity of a discrete memoryless channel, a quantit…
Hardening RGB-D Object Recognition Systems against Adversarial Patch Attacks
Yang Zheng, Luca Demetrio, Antonio Emanuele Cinà +6
RGB-D object recognition systems improve their predictive performances by fusing color and depth information, outperforming neural network architectures that rely solely on colors.…
Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training
Dario Lazzaro, Antonio Emanuele Cinà, Maura Pintor +4
Deep learning models undergo a significant increase in the number of parameters they possess, leading to the execution of a larger number of operations during inference. This expan…
On the Limitations of Model Stealing with Uncertainty Quantification Models
David Pape, Sina Däubener, Thorsten Eisenhofer +2
Model stealing aims at inferring a victim model's functionality at a fraction of the original training cost. While the goal is clear, in practice the model's architecture, weight d…
Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
Antonio Emanuele Cinà, Kathrin Grosse, Ambra Demontis +7
The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update exi…
Machine Learning Security against Data Poisoning: Are We There Yet?
Antonio Emanuele Cinà, Kathrin Grosse, Ambra Demontis +3
The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the…
Energy-Latency Attacks via Sponge Poisoning
Antonio Emanuele Cinà, Ambra Demontis, Battista Biggio +2
Sponge examples are test-time inputs optimized to increase energy consumption and prediction latency of deep networks deployed on hardware accelerators. By increasing the fraction…
Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions
Antonio Emanuele Cinà, Kathrin Grosse, Sebastiano Vascon +4
Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at…
The Hammer and the Nut: Is Bilevel Optimization Really Needed to Poison Linear Classifiers?
Antonio Emanuele Cinà, Sebastiano Vascon, Ambra Demontis +3
One of the most concerning threats for modern AI systems is data poisoning, where the attacker injects maliciously crafted training data to corrupt the system's behavior at test ti…
A black-box adversarial attack for poisoning clustering
Antonio Emanuele Cinà, Alessandro Torcinovich, Marcello Pelillo
Clustering algorithms play a fundamental role as tools in decision-making and sensible automation processes. Due to the widespread use of these applications, a robustness analysis…