LPLuca Pajola

Luca Pajola

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Luca Pajola has a total of 44 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    The Hidden Threat in Plain Text: Attacking RAG Data Loaders

    by Alberto Castagnaro, Umberto Salviati, Mauro Conti, Luca Pajola, Simeone Pizzi


  • Open Access

    E-PhishGEN: Unlocking Novel Research in Phishing Email Detection

    by Luca Pajola, Eugenio Caripoti, Stefan Banzer, Simeone Pizzi, Mauro Conti, Giovanni Apruzzese


  • DUMB and DUMBer: Is Adversarial Training Worth It in the Real World?

    by Francesco Marchiori, Marco Alecci, Luca Pajola, Mauro Conti


  • Exploiting Artificial Intelligence for Attacks: On the Interplay Between Adversarial Artificial Intelligence and Offensive Artificial Intelligence

    by Saskia Laura Schröer, Luca Pajola, Alberto Castagnaro, Giovanni Apruzzese, Mauro Conti

    As Artificial Intelligence (AI) continues to evolve, it has transitioned from a research-focused discipline to a widely adopted technology, enabling intelligent solutions across various sectors. In security, AI’s role in strengthening organizational resilience has been studied for over two decades. While much attention has focused on AI’s constructive applications, the increasing maturity and integration of AI have also exposed its darker potentials. This article explores two emerging AI-related threats and the interplay between them: AI as a target of attacks (‘Adversarial AI’) and AI as a means to launch attacks on any target (‘Offensive AI’) – potentially even on another AI. By cutting through the confusion and explaining these threats in plain terms, we introduce the complex and often misunderstood interplay between Adversarial AI and Offensive AI, offering a clear and accessible introduction to the challenges posed by these threats.

  • Open Access

    The Hidden Threat in Plain Text: Attacking RAG Data Loaders

    by Alberto Castagnaro, Umberto Salviati, Mauro Conti, Luca Pajola, Simeone Pizzi

    Large Language Models (LLMs) have transformed human-machine interaction since ChatGPT's 2022 debut, with Retrieval-Augmented Generation (RAG) emerging as a key framework that enhances LLM outputs by integrating external knowledge. However, RAG's reliance on ingesting external documents introduces new vulnerabilities. This paper exposes a critical security gap at the data loading stage, where malicious actors can stealthily corrupt RAG pipelines by exploiting document ingestion. We propose a taxonomy of 9 knowledge-based poisoning attacks and introduce two novel threat vectors -- Content Obfuscation and Content Injection -- targeting common formats (DOCX, HTML, PDF). Using an automated toolkit implementing 19 stealthy injection techniques, we test five popular data loaders, finding a 74.4% attack success rate across 357 scenarios. We further validate these threats on six end-to-end RAG systems -- including white-box pipelines and black-box services like NotebookLM and OpenAI Assistants -- demonstrating high success rates and critical vulnerabilities that bypass filters and silently compromise output integrity. Our results emphasize the urgent need to secure the document ingestion process in RAG systems against covert content manipulations.

  • Open Access

    DUMB and DUMBer: Is Adversarial Training Worth It in the Real World?

    by Francesco Marchiori, Marco Alecci, Luca Pajola, Mauro Conti

    Adversarial examples are small and often imperceptible perturbations crafted to fool machine learning models. These attacks seriously threaten the reliability of deep neural networks, especially in security-sensitive domains. Evasion attacks, a form of adversarial attack where input is modified at test time to cause misclassification, are particularly insidious due to their transferability: adversarial examples crafted against one model often fool other models as well. This property, known as adversarial transferability, complicates defense strategies since it enables black-box attacks to succeed without direct access to the victim model. While adversarial training is one of the most widely adopted defense mechanisms, its effectiveness is typically evaluated on a narrow and homogeneous population of models. This limitation hinders the generalizability of empirical findings and restricts practical adoption. In this work, we introduce DUMBer, an attack framework built on the foundation of the DUMB (Dataset soUrces, Model architecture, and Balance) methodology, to systematically evaluate the resilience of adversarially trained models. Our testbed spans multiple adversarial training techniques evaluated across three diverse computer vision tasks, using a heterogeneous population of uniquely trained models to reflect real-world deployment variability. Our experimental pipeline comprises over 130k evaluations spanning 13 state-of-the-art attack algorithms, allowing us to capture nuanced behaviors of adversarial training under varying threat models and dataset conditions. Our findings offer practical, actionable insights for AI practitioners, identifying which defenses are most effective based on the model, dataset, and attacker setup.

  • Open Access

    Offensive AI: Enhancing Directory Brute-forcing Attack with the Use of Language Models

    by Alberto Castagnaro, Mauro Conti, Luca Pajola

    Web Vulnerability Assessment and Penetration Testing (Web VAPT) is a comprehensive cybersecurity process that uncovers a range of vulnerabilities which, if exploited, could compromise the integrity of web applications. In a VAPT, it is common to perform a Directory brute-forcing Attack, aiming at the identification of accessible directories of a target website. Current commercial solutions are inefficient as they are based on brute-forcing strategies that use wordlists, resulting in enormous quantities of trials for a small amount of success. Offensive AI is a recent paradigm that integrates AI-based technologies in cyber attacks. In this work, we explore whether AI can enhance the directory enumeration process and propose a novel Language Model-based framework. Our experiments -- conducted in a testbed consisting of 1 million URLs from different web application domains (universities, hospitals, government, companies) -- demonstrate the superiority of the LM-based attack, with an average performance increase of 969%.


  • Lights Toward Adversarial Machine Learning: The Achilles Heel of Artificial Intelligence

    by Luca Pajola, Mauro Conti

    Artificial intelligence (AI)-based technologies are starting to be adopted in the industrial world in many different contexts and sectors, from health care to the automotive, from agriculture to the industrial. As such applications operate in sensitive contexts, it is natural to question: Are they cyber-secure? Can attackers exploit AI applications for their attack? In this work, we discuss the Achilles heel of artificial intelligence: the “adversarial machine learning.” From a cybersecurity practitioner’s point of view, we discuss threats related to AI applications that include each component involved in the AI process, from the operative systems and libraries utilized to deploy the AI application, to the actual AI lifecycle.


  • Open Access

    "All of Me": Mining Users' Attributes from their Public Spotify Playlists

    by Pier Paolo Tricomi, Luca Pajola, Luca Pasa, Mauro Conti

    In the age of digital music streaming, playlists on platforms like Spotify have become an integral part of individuals' musical experiences. People create and publicly share their own playlists to express their musical tastes, promote the discovery of their favorite artists, and foster social connections. In this work, we aim to address the question: can we infer users' private attributes from their public Spotify playlists? To this end, we conducted an online survey involving 739 Spotify users, resulting in a dataset of 10,286 publicly shared playlists comprising over 200,000 unique songs and 55,000 artists. Then, we utilize statistical analyses and machine learning algorithms to build accurate predictive models for users' attributes.


  • Open Access

    Offensive AI: Enhancing Directory Brute-forcing Attack with the Use of Language Models

    by Alberto Castagnaro, Mauro Conti, Luca Pajola

    Web Vulnerability Assessment and Penetration Testing (Web VAPT) is a comprehensive cybersecurity process that uncovers a range of vulnerabilities which, if exploited, could compromise the integrity of web applications. In a VAPT, it is common to perform a \textit{Directory brute-forcing Attack}, aiming at the identification of accessible directories of a target website. Current commercial solutions are inefficient as they are based on brute-forcing strategies that use wordlists, resulting in enormous quantities of trials for a small amount of success. Offensive AI is a recent paradigm that integrates AI-based technologies in cyber attacks. In this work, we explore whether AI can enhance the directory enumeration process and propose a novel Language Model-based framework. Our experiments -- conducted in a testbed consisting of 1 million URLs from different web application domains (universities, hospitals, government, companies) -- demonstrate the superiority of the LM-based attack, with an average performance increase of 969%.