Searcharxiv⌕ Search

arXiv subjects

Marco Arazzi

Publications and source records attributed to Marco Arazzi.

At least 19 recordsLinked to original sources
arXiv2026

An AI-Based Solution for Secure Service Provisioning in IoT

As the Internet of Things (IoT) continues its rapid expansion, the attack surface grows accordingly, with emerging threats targeting smart objects and their interactions. In this evolving landscape, securing service provisioning is crucial to ensure the proper functioning, security, and reliability of the IoT ecosystem. Service provisioning encompasses key tasks such as device registration, configuration, authentication, authorization, and software deployment, all of which are essential for seamless and secure IoT operations. In this paper, we present a comprehensive framework designed to select the most suitable smart objects to deliver a target service within a given IoT environment while also monitoring the behavior of the entities involved during the service provisioning phase. To achieve this, we employ a Deep Reinforcement Learning (DRL) approach in which an intelligent agent learns, through interaction with a complex, dynamic environment, how to adapt to changes while adhering to predefined security constraints. For behavioral monitoring, we leverage Federated Learning (FL) to develop a global Behavioral Fingerprinting (BF) model that is fully distributed and can analyze how IoT devices interact within the network. In addition, the BF is used to compute a reliability score for each service provider, reflecting its degree of compliance with the defined security constraints. This score is then incorporated into the service provisioning process, allowing smart objects to select providers not only according to functional suitability but also to their reliability level. Finally, we conduct an extensive experimental evaluation to assess the robustness and scalability of our approach. The results demonstrate that our solution can be effectively deployed even on resource-constrained IoT devices, making it a viable and scalable security-enhancing mechanism for modern IoT ecosystems.

cs.CR↗
arXiv2026

You Snooze, You Lose: Automatic Safety Alignment Restoration through Neural Weight Translation

Public repositories now distribute thousands of specialized Low-Rank Adaptation (LoRA) modules, but a third-party adapter routinely arrives without the refusal behavior the same adapter would have had if it had been trained responsibly. Restoring it by fine-tuning on safety data induces the opposite failure: the domain expertise the adapter was published to provide degrades. A practitioner who downloads a finished adapter holds neither the domain corpus nor a safety corpus, so neither remedy is available. We propose Neural Weight Translation (NeWTral), which maps unsafe domain adapters to their safety-aligned counterparts entirely within parameter space while preserving their expertise. NeWTral is a non-linear translator pre-trained on unsafe-to-safe adapter pairs, with a Mixture of Experts router that blends a high-fidelity surgical translator and an aggressive alignment expert per tensor. Across four architectural families (Llama, Mistral, Qwen, Gemma) at scales up to 72B parameters and eight professional domains, NeWTral cuts the average Attack Success Rate from 70% to 13% while retaining 88% knowledge fidelity. The effect reproduces on JailbreakBench, on 12 of 14 adapters downloaded from a public model hub, and under automated jailbreak attacks. Curing is a single pass over the weights, needing no original training data and no retraining.

cs.CR↗
arXiv2026

Security in LLM-as-a-Judge: A Comprehensive SoK

LLM-as-a-Judge (LaaJ) is a novel paradigm in which powerful language models are used to assess the quality, safety, or correctness of generated outputs. While this paradigm has significantly improved the scalability and efficiency of evaluation processes, it also introduces novel security risks and reliability concerns that remain largely unexplored. In particular, LLM-based judges can become both targets of adversarial manipulation and instruments through which attacks are conducted, potentially compromising the trustworthiness of evaluation pipelines. In this paper, we present the first Systematization of Knowledge (SoK) focusing on the security aspects of LLM-as-a-Judge systems. We perform a comprehensive literature review across major academic databases, analyzing 863 works and selecting 45 relevant studies published between 2020 and 2026. Based on this study, we propose a taxonomy that organizes recent research according to the role played by LLM-as-a-Judge in the security landscape, distinguishing between attacks targeting LaaJ systems, attacks performed through LaaJ, defenses leveraging LaaJ for security purposes, and applications where LaaJ is used as an evaluation strategy in security-related domains. We further provide a comparative analysis of existing approaches, highlighting current limitations, emerging threats, and open research challenges. Our findings reveal significant vulnerabilities in LLM-based evaluation frameworks, as well as promising directions for improving their robustness and reliability. Finally, we outline key research opportunities that can guide the development of more secure and trustworthy LLM-as-a-Judge systems.

cs.CR↗
arXiv2026

SecureBreak -- A dataset towards safe and secure models

Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Although previous related works focused primarily on model architectures and alignment methodologies, these approaches alone cannot ensure the complete elimination of harmful generations. This concern is reinforced by the growing body of scientific literature showing that attacks, such as jailbreaking and prompt injection, can bypass existing security alignment mechanisms. As a consequence, additional security strategies are needed both to provide qualitative feedback on the robustness of the obtained security alignment at the training stage, and to create an ``ultimate'' defense layer to block unsafe outputs possibly produced by deployed models. To provide a contribution in this scenario, this paper introduces SecureBreak, a safety-oriented dataset designed to support the development of AI-driven solutions for detecting harmful LLM outputs caused by residual weaknesses in security alignment. The dataset is highly reliable due to careful manual annotation, where labels are assigned conservatively to ensure safety. It performs well in detecting unsafe content across multiple risk categories. Tests with pre-trained LLMs show improved results after fine-tuning on SecureBreak. Overall, the dataset is useful both for post-generation safety filtering and for guiding further model alignment and security improvements.

cs.CR↗
arXiv2026

Exploring Structural Complexity in Normative RAG with Graph-based approaches: A case study on the ETSI Standards

Industrial standards and normative documents exhibit intricate hierarchical structures, domain-specific lexicons, and extensive cross-referential dependencies, which making it challenging to process them directly by Large Language Models (LLMs). While Retrieval-Augmented Generation (RAG) provides a computationally efficient alternative to LLM fine-tuning, standard "vanilla" vector-based retrieval may fail to capture the latent structural and relational features intrinsic in normative documents. With the objective of shedding light on the most promising technique for building high-performance RAG solutions for normative, standards, and regulatory documents, this paper investigates the efficacy of Graph RAG architectures, which represent information as interconnected nodes, thus moving from simple semantic similarity toward a more robust, relation-aware retrieval mechanism. Despite the promise of graph-based techniques, there is currently a lack of empirical evidence as to which is the optimal indexing strategy for technical standards. Therefore, to help solve this knowledge gap, we propose a specialized RAG methodology tailored to the unique structure and lexical characteristics of standards and regulatory documents. Moreover, to keep our investigation grounded, we focus on well-known public standards, such as the ETSI EN 301 489 series. We evaluate several lightweight and low-latency strategies designed to embed document structure directly into the retrieval workflow. The considered approaches are rigorously tested against a custom synthesized Q&A dataset, facilitating a quantitative performance analysis. Our experimental results demonstrate that the incorporation of structural and lexical information into the index can enhance, at least to some extent, retrieval performance, providing a scalable framework for automated normative and standards elaboration.

cs.IR↗
arXiv2026

SD-RAG: A Prompt-Injection-Resilient Framework for Selective Disclosure in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) has attracted significant attention due to its ability to combine the generative capabilities of Large Language Models (LLMs) with knowledge obtained through efficient retrieval mechanisms over large-scale data collections. Currently, the majority of existing approaches overlook the risks associated with exposing sensitive or access-controlled information directly to the generation model. Only a few approaches propose techniques to instruct the generative model to refrain from disclosing sensitive information; however, recent studies have also demonstrated that LLMs remain vulnerable to prompt injection attacks that can override intended behavioral constraints. For these reasons, we propose a novel approach to Selective Disclosure in Retrieval-Augmented Generation, called SD-RAG, which decouples the enforcement of security and privacy constraints from the generation process itself. Rather than relying on prompt-level safeguards, SD-RAG applies sanitization and disclosure controls during the retrieval phase, prior to augmenting the language model's input. Moreover, we introduce a semantic mechanism to allow the ingestion of human-readable dynamic security and privacy constraints together with an optimized graph-based data model that supports fine-grained, policy-aware retrieval. Our experimental evaluation demonstrates the superiority of SD-RAG over baseline existing approaches, achieving up to a $58\%$ improvement in the privacy score, while also showing a strong resilience to prompt injection attacks targeting the generative model.

cs.CR↗
arXiv2026

LoRA as Oracle

Practitioners increasingly deploy neural networks they did not train, and must audit them after the fact for hidden backdoors, without the training pipeline, the poisoned data, or knowledge of any trigger. We introduce a low-rank auditing lens built on a single observation: what a model has internalized and how it behaves are distinct axes that can diverge. Fitting a small low-rank adapter toward a hypothesis and reading the geometry of the resulting update, its energy relative to, and its alignment with, the frozen weights, measures internalization directly, independently of the model's output behavior. The lens earns its value where the two axes diverge: a backdoor is malicious internalization, a learned trigger-to-target shortcut, that behavioral auditing can miss. Reading it, we identify the backdoor's target class label-free and without any triggered data when the backdoor leaves a legible internalization signature, then erase the identified shortcut within the same low-rank subspace, uniquely coupling detection confidence to the size of the repair. Across four datasets and four architectures, our lens is the most consistent target identifier among defenses in its threat model; its rank-r repair removes backdoors while preserving clean accuracy where full-model baselines collapse it, at orders-of-magnitude lower parameter and memory cost; and it is the only method that both erases the backdoor and leaves a benign model intact, because it can decline to act when uncertain.

cs.CR↗
arXiv2025

SoK: The Last Line of Defense: On Backdoor Defense Evaluation

Backdoor attacks pose a significant threat to deep learning models by implanting hidden vulnerabilities that can be activated by malicious inputs. While numerous defenses have been proposed to mitigate these attacks, the heterogeneous landscape of evaluation methodologies hinders fair comparison between defenses. This work presents a systematic (meta-)analysis of backdoor defenses through a comprehensive literature review and empirical evaluation. We analyzed 183 backdoor defense papers published between 2018 and 2025 across major AI and security venues, examining the properties and evaluation methodologies of these defenses. Our analysis reveals significant inconsistencies in experimental setups, evaluation metrics, and threat model assumptions in the literature. Through extensive experiments involving three datasets (MNIST, CIFAR-100, ImageNet-1K), four model architectures (ResNet-18, VGG-19, ViT-B/16, DenseNet-121), 16 representative defenses, and five commonly used attacks, totaling over 3\,000 experiments, we demonstrate that defense effectiveness varies substantially across different evaluation setups. We identify critical gaps in current evaluation practices, including insufficient reporting of computational overhead and behavior under benign conditions, bias in hyperparameter selection, and incomplete experimentation. Based on our findings, we provide concrete challenges and well-motivated recommendations to standardize and improve future defense evaluations. Our work aims to equip researchers and industry practitioners with actionable insights for developing, assessing, and deploying defenses to different systems.

cs.CR↗
arXiv2025

When Forgetting Triggers Backdoors: A Clean Unlearning Attack

Machine unlearning has emerged as a key component in ensuring ``Right to be Forgotten'', enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set (clean unlearning), it can be exploited for stealthy attacks that existing defenses struggle to detect. In this paper, we propose a novel {\em clean} backdoor attack that exploits both the model learning phase and the subsequent unlearning requests. Unlike traditional backdoor methods, during the first phase, our approach injects a weak, distributed malicious signal across multiple classes. The real attack is then activated and amplified by selectively unlearning {\em non-poisoned} samples. This strategy results in a powerful and stealthy novel attack that is hard to detect or mitigate, highlighting critical vulnerabilities in current unlearning mechanisms and highlighting the need for more robust defenses.

cs.CR↗
arXiv2025

XBreaking: Understanding how LLMs security alignment can be broken

Large Language Models are fundamental actors in the modern IT landscape dominated by AI solutions. However, security threats associated with them might prevent their reliable adoption in critical application scenarios such as government organizations and medical institutions. For this reason, commercial LLMs typically undergo a sophisticated censoring mechanism to eliminate any harmful output they could possibly produce. These mechanisms maintain the integrity of LLM alignment by guaranteeing that the models respond safely and ethically. In response to this, attacks on LLMs are a significant threat to such protections, and many previous approaches have already demonstrated their effectiveness across diverse domains. Existing LLM attacks mostly adopt a generate-and-test strategy to craft malicious input. To improve the comprehension of censoring mechanisms and design a targeted attack, we propose an Explainable-AI solution that comparatively analyzes the behavior of censored and uncensored models to derive unique exploitable alignment patterns. Then, we propose XBreaking, a novel approach that exploits these unique patterns to break the security and alignment constraints of LLMs by targeted noise injection. Our thorough experimental campaign returns important insights about the censoring mechanisms and demonstrates the effectiveness and performance of our approach.

cs.CR↗
arXiv2025

DroidTTP: Mapping Android Applications with TTP for Cyber Threat Intelligence

The widespread adoption of Android devices for sensitive operations like banking and communication has made them prime targets for cyber threats, particularly Advanced Persistent Threats (APT) and sophisticated malware attacks. Traditional malware detection methods rely on binary classification, failing to provide insights into adversarial Tactics, Techniques, and Procedures (TTPs). Understanding malware behavior is crucial for enhancing cybersecurity defenses. To address this gap, we introduce DroidTTP, a framework mapping Android malware behaviors to TTPs based on the MITRE ATT&CK framework. Our curated dataset explicitly links MITRE TTPs to Android applications. We developed an automated solution leveraging the Problem Transformation Approach (PTA) and Large Language Models (LLMs) to map applications to both Tactics and Techniques. Additionally, we employed Retrieval-Augmented Generation (RAG) with prompt engineering and LLM fine-tuning for TTP predictions. Our structured pipeline includes dataset creation, hyperparameter tuning, data augmentation, feature selection, model development, and SHAP-based model interpretability. Among LLMs, Llama achieved the highest performance in Tactic classification with a Jaccard Similarity of 0.9583 and Hamming Loss of 0.0182, and in Technique classification with a Jaccard Similarity of 0.9348 and Hamming Loss of 0.0127. However, the Label Powerset XGBoost model outperformed LLMs, achieving a Jaccard Similarity of 0.9893 for Tactic classification and 0.9753 for Technique classification, with a Hamming Loss of 0.0054 and 0.0050, respectively. While XGBoost showed superior performance, the narrow margin highlights the potential of LLM-based approaches in TTP classification.

cs.CR↗
arXiv2025

Privacy Preserving and Robust Aggregation for Cross-Silo Federated Learning in Non-IID Settings

Federated Averaging remains the most widely used aggregation strategy in federated learning due to its simplicity and scalability. However, its performance degrades significantly in non-IID data settings, where client distributions are highly imbalanced or skewed. Additionally, it relies on clients transmitting metadata, specifically the number of training samples, which introduces privacy risks and may conflict with regulatory frameworks like the European GDPR. In this paper, we propose a novel aggregation strategy that addresses these challenges by introducing class-aware gradient masking. Unlike traditional approaches, our method relies solely on gradient updates, eliminating the need for any additional client metadata, thereby enhancing privacy protection. Furthermore, our approach validates and dynamically weights client contributions based on class-specific importance, ensuring robustness against non-IID distributions, convergence prevention, and backdoor attacks. Extensive experiments on benchmark datasets demonstrate that our method not only outperforms FedAvg and other widely accepted aggregation strategies in non-IID settings but also preserves model integrity in adversarial scenarios. Our results establish the effectiveness of gradient masking as a practical and secure solution for federated learning.

cs.LG↗
arXiv2025

Secure Federated Data Distillation

Dataset Distillation (DD) is a powerful technique for reducing large datasets into compact, representative synthetic datasets, accelerating Machine Learning training. However, traditional DD methods operate in a centralized manner, which poses significant privacy threats and reduces its applicability. To mitigate these risks, we propose a Secure Federated Data Distillation (SFDD) framework to decentralize the distillation process while preserving privacy. Unlike existing Federated Distillation techniques that focus on training global models with distilled knowledge, our approach aims to produce a distilled dataset without exposing local contributions. We leverage the gradient-matching-based distillation method, adapting it for a distributed setting where clients contribute to the distillation process without sharing raw data. The central aggregator iteratively refines a synthetic dataset by integrating client-side updates while ensuring data confidentiality. To make our approach resilient to inference attacks perpetrated by the server that could exploit gradient updates to reconstruct private data, we create an optimized Local Differential Privacy approach, called LDPO-RLD. Furthermore, we assess the framework's resilience against malicious clients executing backdoor attacks (such as Doorping) and demonstrate robustness under the assumption of a sufficient number of participating clients. Our experimental results demonstrate the effectiveness of SFDD and that the proposed defense concretely mitigates the identified vulnerabilities, with minimal impact on the performance of the distilled dataset. By addressing the interplay between privacy and federation in dataset distillation, this work advances the field of privacy-preserving Machine Learning making our SFDD framework a viable solution for sensitive data-sharing applications.

cs.CR↗
arXiv2025

Augmented Knowledge Graph Querying leveraging LLMs

Adopting Knowledge Graphs (KGs) as a structured, semantic-oriented, data representation model has significantly improved data integration, reasoning, and querying capabilities across different domains. This is especially true in modern scenarios such as Industry 5.0, in which the integration of data produced by humans, smart devices, and production processes plays a crucial role. However, the management, retrieval, and visualization of data from a KG using formal query languages can be difficult for non-expert users due to their technical complexity, thus limiting their usage inside industrial environments. For this reason, we introduce SparqLLM, a framework that utilizes a Retrieval-Augmented Generation (RAG) solution, to enhance the querying of Knowledge Graphs (KGs). SparqLLM executes the Extract, Transform, and Load (ETL) pipeline to construct KGs from raw data. It also features a natural language interface powered by Large Language Models (LLMs) to enable automatic SPARQL query generation. By integrating template-based methods as retrieved-context for the LLM, SparqLLM enhances query reliability and reduces semantic errors, ensuring more accurate and efficient KG interactions. Moreover, to improve usability, the system incorporates a dynamic visualization dashboard that adapts to the structure of the retrieved data, presenting the query results in an intuitive format. Rigorous experimental evaluations demonstrate that SparqLLM achieves high query accuracy, improved robustness, and user-friendly interaction with KGs, establishing it as a scalable solution to access semantic data.

cs.IR↗
arXiv2024

Subject Data Auditing via Source Inference Attack in Cross-Silo Federated Learning

Source Inference Attack (SIA) in Federated Learning (FL) aims to identify which client used a target data point for local model training. It allows the central server to audit clients' data usage. In cross-silo FL, a client (silo) collects data from multiple subjects (e.g., individuals, writers, or devices), posing a risk of subject information leakage. Subject Membership Inference Attack (SMIA) targets this scenario and attempts to infer whether any client utilizes data points from a target subject in cross-silo FL. However, existing results on SMIA are limited and based on strong assumptions on the attack scenario. Therefore, we propose a Subject-Level Source Inference Attack (SLSIA) by removing critical constraints that only one client can use a target data point in SIA and imprecise detection of clients utilizing target subject data in SMIA. The attacker, positioned on the server side, controls a target data source and aims to detect all clients using data points from the target subject. Our strategy leverages a binary attack classifier to predict whether the embeddings returned by a local model on test data from the target subject include unique patterns that indicate a client trains the model with data from that subject. To achieve this, the attacker locally pre-trains models using data derived from the target subject and then leverages them to build a training set for the binary attack classifier. Our SLSIA significantly outperforms previous methods on three datasets. Specifically, SLSIA achieves a maximum average accuracy of 0.88 over 50 target subjects. Analyzing embedding distribution and input feature distance shows that datasets with sparse subjects are more susceptible to our attack. Finally, we propose to defend our SLSIA using item-level and subject-level differential privacy mechanisms.

cs.CR↗
arXiv2024

Let's Focus: Focused Backdoor Attack against Federated Transfer Learning

Federated Transfer Learning (FTL) is the most general variation of Federated Learning. According to this distributed paradigm, a feature learning pre-step is commonly carried out by only one party, typically the server, on publicly shared data. After that, the Federated Learning phase takes place to train a classifier collaboratively using the learned feature extractor. Each involved client contributes by locally training only the classification layers on a private training set. The peculiarity of an FTL scenario makes it hard to understand whether poisoning attacks can be developed to craft an effective backdoor. State-of-the-art attack strategies assume the possibility of shifting the model attention toward relevant features introduced by a forged trigger injected in the input data by some untrusted clients. Of course, this is not feasible in FTL, as the learned features are fixed once the server performs the pre-training step. Consequently, in this paper, we investigate this intriguing Federated Learning scenario to identify and exploit a vulnerability obtained by combining eXplainable AI (XAI) and dataset distillation. In particular, the proposed attack can be carried out by one of the clients during the Federated Learning phase of FTL by identifying the optimal local for the trigger through XAI and encapsulating compressed information of the backdoor class. Due to its behavior, we refer to our approach as a focused backdoor approach (FB-FTL for short) and test its performance by explicitly referencing an image classification scenario. With an average 80% attack success rate, obtained results show the effectiveness of our attack also against existing defenses for Federated Learning.

cs.LG↗
arXiv2024

KDk: A Defense Mechanism Against Label Inference Attacks in Vertical Federated Learning

Vertical Federated Learning (VFL) is a category of Federated Learning in which models are trained collaboratively among parties with vertically partitioned data. Typically, in a VFL scenario, the labels of the samples are kept private from all the parties except for the aggregating server, that is the label owner. Nevertheless, recent works discovered that by exploiting gradient information returned by the server to bottom models, with the knowledge of only a small set of auxiliary labels on a very limited subset of training data points, an adversary can infer the private labels. These attacks are known as label inference attacks in VFL. In our work, we propose a novel framework called KDk, that combines Knowledge Distillation and k-anonymity to provide a defense mechanism against potential label inference attacks in a VFL scenario. Through an exhaustive experimental campaign we demonstrate that by applying our approach, the performance of the analyzed label inference attacks decreases consistently, even by more than 60%, maintaining the accuracy of the whole VFL almost unaltered.

cs.LG↗
arXiv2024

A Deep Reinforcement Learning Approach for Security-Aware Service Acquisition in IoT

The novel Internet of Things (IoT) paradigm is composed of a growing number of heterogeneous smart objects and services that are transforming architectures and applications, increasing systems' complexity, and the need for reliability and autonomy. In this context, both smart objects and services are often provided by third parties which do not give full transparency regarding the security and privacy of the features offered. Although machine-based Service Level Agreements (SLA) have been recently leveraged to establish and share policies in Cloud-based scenarios, and also in the IoT context, the issue of making end users aware of the overall system security levels and the fulfillment of their privacy requirements through the provision of the requested service remains a challenging task. To tackle this problem, we propose a complete framework that defines suitable levels of privacy and security requirements in the acquisition of services in IoT, according to the user needs. Through the use of a Reinforcement Learning based solution, a user agent, inside the environment, is trained to choose the best smart objects granting access to the target services. Moreover, the solution is designed to guarantee deadline requirements and user security and privacy needs. Finally, to evaluate the correctness and the performance of the proposed approach we illustrate an extensive experimental analysis.

cs.CR↗