arXiv subjects

Fabio Roli

Publications and source records attributed to Fabio Roli.

At least 37 records · Page 2Linked to original sources

arXiv2025

Attention-based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devices

Due to great success of transformers in many applications such as natural language processing and computer vision, transformers have been successfully applied in automatic modulation classification. We have shown that transformer-based radio signal classification is vulnerable to imperceptible and carefully crafted attacks called adversarial examples. Therefore, we propose a defense system against adversarial examples in transformer-based modulation classifications. Considering the need for computationally efficient architecture particularly for Internet of Things (IoT)-based applications or operation of devices in environment where power supply is limited, we propose a compact transformer for modulation classification. The advantages of robust training such as adversarial training in transformers may not be attainable in compact transformers. By demonstrating this, we propose a novel compact transformer that can enhance robustness in the presence of adversarial attacks. The new method is aimed at transferring the adversarial attention map from the robustly trained large transformer to a compact transformer. The proposed method outperforms the state-of-the-art techniques for the considered white-box scenarios including fast gradient method and projected gradient descent attacks. We have provided reasoning of the underlying working mechanisms and investigated the transferability of the adversarial examples between different architectures. The proposed method has the potential to protect the transformer from the transferability of adversarial examples.

cs.LG↗

arXiv2025

A Neural Rejection System Against Universal Adversarial Perturbations in Radio Signal Classification

Advantages of deep learning over traditional methods have been demonstrated for radio signal classification in the recent years. However, various researchers have discovered that even a small but intentional feature perturbation known as adversarial examples can significantly deteriorate the performance of the deep learning based radio signal classification. Among various kinds of adversarial examples, universal adversarial perturbation has gained considerable attention due to its feature of being data independent, hence as a practical strategy to fool the radio signal classification with a high success rate. Therefore, in this paper, we investigate a defense system called neural rejection system to propose against universal adversarial perturbations, and evaluate its performance by generating white-box universal adversarial perturbations. We show that the proposed neural rejection system is able to defend universal adversarial perturbations with significantly higher accuracy than the undefended deep neural network.

cs.LG↗

arXiv2025

Vision Transformer with Adversarial Indicator Token against Adversarial Attacks in Radio Signal Classifications

The remarkable success of transformers across various fields such as natural language processing and computer vision has paved the way for their applications in automatic modulation classification, a critical component in the communication systems of Internet of Things (IoT) devices. However, it has been observed that transformer-based classification of radio signals is susceptible to subtle yet sophisticated adversarial attacks. To address this issue, we have developed a defensive strategy for transformer-based modulation classification systems to counter such adversarial attacks. In this paper, we propose a novel vision transformer (ViT) architecture by introducing a new concept known as adversarial indicator (AdvI) token to detect adversarial attacks. To the best of our knowledge, this is the first work to propose an AdvI token in ViT to defend against adversarial attacks. Integrating an adversarial training method with a detection mechanism using AdvI token, we combine a training time defense and running time defense in a unified neural network model, which reduces architectural complexity of the system compared to detecting adversarial perturbations using separate models. We investigate into the operational principles of our method by examining the attention mechanism. We show the proposed AdvI token acts as a crucial element within the ViT, influencing attention weights and thereby highlighting regions or features in the input data that are potentially suspicious or anomalous. Through experimental results, we demonstrate that our approach surpasses several competitive methods in handling white-box attack scenarios, including those utilizing the fast gradient method, projected gradient descent attacks and basic iterative method.

cs.LG↗

arXiv2025

Empirical Quantification of Spurious Correlations in Malware Detection

End-to-end deep learning exhibits unmatched performance for detecting malware, but such an achievement is reached by exploiting spurious correlations -- features with high relevance at inference time, but known to be useless through domain knowledge. While previous work highlighted that deep networks mainly focus on metadata, none investigated the phenomenon further, without quantifying their impact on the decision. In this work, we deepen our understanding of how spurious correlation affects deep learning for malware detection by highlighting how much models rely on empty spaces left by the compiler, which diminishes the relevance of the compiled code. Through our seminal analysis on a small-scale balanced dataset, we introduce a ranking of two end-to-end models to better understand which is more suitable to be put in production.

cs.CR↗

arXiv2025

Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness

Recent work has proposed neural network pruning techniques to reduce the size of a network while preserving robustness against adversarial examples, i.e., well-crafted inputs inducing a misclassification. These methods, which we refer to as adversarial pruning methods, involve complex and articulated designs, making it difficult to analyze the differences and establish a fair and accurate comparison. In this work, we overcome these issues by surveying current adversarial pruning methods and proposing a novel taxonomy to categorize them based on two main dimensions: the pipeline, defining when to prune; and the specifics, defining how to prune. We then highlight the limitations of current empirical analyses and propose a novel, fair evaluation benchmark to address them. We finally conduct an empirical re-evaluation of current adversarial pruning methods and discuss the results, highlighting the shared traits of top-performing adversarial pruning methods, as well as common issues. We welcome contributions in our publicly-available benchmark at https://github.com/pralab/AdversarialPruningBenchmark

cs.LG↗

arXiv2025

Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates

Machine-learning models demand periodic updates to improve their average accuracy, exploiting novel architectures and additional data. However, a newly updated model may commit mistakes the previous model did not make. Such misclassifications are referred to as negative flips, experienced by users as a regression of performance. In this work, we show that this problem also affects robustness to adversarial examples, hindering the development of secure model update practices. In particular, when updating a model to improve its adversarial robustness, previously ineffective adversarial attacks on some inputs may become successful, causing a regression in the perceived security of the system. We propose a novel technique, named robustness-congruent adversarial training, to address this issue. It amounts to fine-tuning a model with adversarial training, while constraining it to retain higher robustness on the samples for which no adversarial example was found before the update. We show that our algorithm and, more generally, learning with non-regression constraints, provides a theoretically-grounded framework to train consistent estimators. Our experiments on robust models for computer vision confirm that both accuracy and robustness, even if improved after model update, can be affected by negative flips, and our robustness-congruent adversarial training can mitigate the problem, outperforming competing baseline methods.

cs.LG↗

arXiv2025

On the Robustness of Adversarial Training Against Uncertainty Attacks

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 its wide use, assumes high relevance for security-sensitive applications. Within these scenarios, it becomes fundamental to guarantee good (i.e., trustworthy) uncertainty measures, which downstream modules can securely employ to drive the final decision-making process. However, an attacker may be interested in forcing the system to produce either (i) highly uncertain outputs jeopardizing the system's availability or (ii) low uncertainty estimates, making the system accept uncertain samples that would instead require a careful inspection (e.g., human intervention). Therefore, it becomes fundamental to understand how to obtain robust uncertainty estimates against these kinds of attacks. In this work, we reveal both empirically and theoretically that defending against adversarial examples, i.e., carefully perturbed samples that cause misclassification, additionally guarantees a more secure, trustworthy uncertainty estimate under common attack scenarios without the need for an ad-hoc defense strategy. To support our claims, we evaluate multiple adversarial-robust models from the publicly available benchmark RobustBench on the CIFAR-10 and ImageNet datasets.

cs.LG↗

arXiv2025

AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples

Adversarial examples are typically optimized with gradient-based attacks. While novel attacks are continuously proposed, each is shown to outperform its predecessors using different experimental setups, hyperparameter settings, and number of forward and backward calls to the target models. This provides overly-optimistic and even biased evaluations that may unfairly favor one particular attack over the others. In this work, we aim to overcome these limitations by proposing AttackBench, i.e., the first evaluation framework that enables a fair comparison among different attacks. To this end, we first propose a categorization of gradient-based attacks, identifying their main components and differences. We then introduce our framework, which evaluates their effectiveness and efficiency. We measure these characteristics by (i) defining an optimality metric that quantifies how close an attack is to the optimal solution, and (ii) limiting the number of forward and backward queries to the model, such that all attacks are compared within a given maximum query budget. Our extensive experimental analysis compares more than $100$ attack implementations with a total of over $800$ different configurations against CIFAR-10 and ImageNet models, highlighting that only very few attacks outperform all the competing approaches. Within this analysis, we shed light on several implementation issues that prevent many attacks from finding better solutions or running at all. We release AttackBench as a publicly-available benchmark, aiming to continuously update it to include and evaluate novel gradient-based attacks for optimizing adversarial examples.

cs.LG↗

arXiv2025

Updating Windows Malware Detectors: Balancing Robustness and Regression against Adversarial EXEmples

Adversarial EXEmples are carefully-perturbed programs tailored to evade machine learning Windows malware detectors, with an ongoing effort to develop robust models able to address detection effectiveness. However, even if robust models can prevent the majority of EXEmples, to maintain predictive power over time, models are fine-tuned to newer threats, leading either to partial updates or time-consuming retraining from scratch. Thus, even if the robustness against adversarial EXEmples is higher, the new models might suffer a regression in performance by misclassifying threats that were previously correctly detected. For these reasons, we study the trade-off between accuracy and regression when updating Windows malware detectors by proposing EXE-scanner, a plugin that can be chained to existing detectors to promptly stop EXEmples without causing regression. We empirically show that previously proposed hardening techniques suffer a regression of accuracy when updating non-robust models, exacerbating the gap when considering low false positives regimes and temporal drifts affecting data. Also, through EXE-scanner we gain evidence on the detectability of adversarial EXEmples, showcasing the presence of artifacts left inside while creating them. Due to its design, EXE-scanner can be chained to any classifier to obtain the best performance without the need for costly retraining. To foster reproducibility, we openly release the source code, along with the dataset of adversarial EXEmples based on state-of-the-art perturbation algorithms.

cs.CR↗

arXiv2025

Robust image classification with multi-modal large language models

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 mitigate these vulnerabilities, adversarial training and detection-based defenses have been proposed to strengthen models in advance. However, most of these approaches focus on a single data modality, overlooking the relationships between visual patterns and textual descriptions of the input. In this paper, we propose a novel defense, MultiShield, designed to combine and complement these defenses with multi-modal information to further enhance their robustness. MultiShield leverages multi-modal large language models to detect adversarial examples and abstain from uncertain classifications when there is no alignment between textual and visual representations of the input. Extensive evaluations on CIFAR-10 and ImageNet datasets, using robust and non-robust image classification models, demonstrate that MultiShield can be easily integrated to detect and reject adversarial examples, outperforming the original defenses.

cs.CV↗

arXiv2025

Energy-Latency Attacks via Sponge Poisoning

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 of neurons activated during classification, these attacks reduce sparsity in network activation patterns, worsening the performance of hardware accelerators. In this work, we present a novel training-time attack, named sponge poisoning, which aims to worsen energy consumption and prediction latency of neural networks on any test input without affecting classification accuracy. To stage this attack, we assume that the attacker can control only a few model updates during training -- a likely scenario, e.g., when model training is outsourced to an untrusted third party or distributed via federated learning. Our extensive experiments on image classification tasks show that sponge poisoning is effective, and that fine-tuning poisoned models to repair them poses prohibitive costs for most users, highlighting that tackling sponge poisoning remains an open issue.

cs.CR↗

arXiv2025

SoK: On the Offensive Potential of AI

Our society increasingly benefits from Artificial Intelligence (AI). Unfortunately, more and more evidence shows that AI is also used for offensive purposes. Prior works have revealed various examples of use cases in which the deployment of AI can lead to violation of security and privacy objectives. No extant work, however, has been able to draw a holistic picture of the offensive potential of AI. In this SoK paper we seek to lay the ground for a systematic analysis of the heterogeneous capabilities of offensive AI. In particular we (i) account for AI risks to both humans and systems while (ii) consolidating and distilling knowledge from academic literature, expert opinions, industrial venues, as well as laypeople -- all of which being valuable sources of information on offensive AI. To enable alignment of such diverse sources of knowledge, we devise a common set of criteria reflecting essential technological factors related to offensive AI. With the help of such criteria, we systematically analyze: 95 research papers; 38 InfoSec briefings (from, e.g., BlackHat); the responses of a user study (N=549) entailing individuals with diverse backgrounds and expertise; and the opinion of 12 experts. Our contributions not only reveal concerning ways (some of which overlooked by prior work) in which AI can be offensively used today, but also represent a foothold to address this threat in the years to come.

cs.CR↗

arXiv2025

ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches

Adversarial patches are optimized contiguous pixel blocks in an input image that cause a machine-learning model to misclassify it. However, their optimization is computationally demanding, and requires careful hyperparameter tuning, potentially leading to suboptimal robustness evaluations. To overcome these issues, we propose ImageNet-Patch, a dataset to benchmark machine-learning models against adversarial patches. It consists of a set of patches, optimized to generalize across different models, and readily applicable to ImageNet data after preprocessing them with affine transformations. This process enables an approximate yet faster robustness evaluation, leveraging the transferability of adversarial perturbations. We showcase the usefulness of this dataset by testing the effectiveness of the computed patches against 127 models. We conclude by discussing how our dataset could be used as a benchmark for robustness, and how our methodology can be generalized to other domains. We open source our dataset and evaluation code at https://github.com/pralab/ImageNet-Patch.

cs.CR↗

arXiv2024

SLIFER: Investigating Performance and Robustness of Malware Detection Pipelines

As a result of decades of research, Windows malware detection is approached through a plethora of techniques. However, there is an ongoing mismatch between academia -- which pursues an optimal performances in terms of detection rate and low false alarms -- and the requirements of real-world scenarios. In particular, academia focuses on combining static and dynamic analysis within a single or ensemble of models, falling into several pitfalls like (i) firing dynamic analysis without considering the computational burden it requires; (ii) discarding impossible-to-analyze samples; and (iii) analyzing robustness against adversarial attacks without considering that malware detectors are complemented with more non-machine-learning components. Thus, in this paper we bridge these gaps, by investigating the properties of malware detectors built with multiple and different types of analysis. To do so, we develop SLIFER, a Windows malware detection pipeline sequentially leveraging both static and dynamic analysis, interrupting computations as soon as one module triggers an alarm, requiring dynamic analysis only when needed. Contrary to the state of the art, we investigate how to deal with samples that impede analyzes, showing how much they impact performances, concluding that it is better to flag them as legitimate to not drastically increase false alarms. Lastly, we perform a robustness evaluation of SLIFER. Counter-intuitively, the injection of new content is either blocked more by signatures than dynamic analysis, due to byte artifacts created by the attack, or it is able to avoid detection from signatures, as they rely on constraints on file size disrupted by attacks. As far as we know, we are the first to investigate the properties of sequential malware detectors, shedding light on their behavior in real production environment.

cs.CR↗

arXiv2024

Robust Synthetic Data-Driven Detection of Living-Off-the-Land Reverse Shells

Living-off-the-land (LOTL) techniques pose a significant challenge to security operations, exploiting legitimate tools to execute malicious commands that evade traditional detection methods. To address this, we present a robust augmentation framework for cyber defense systems as Security Information and Event Management (SIEM) solutions, enabling the detection of LOTL attacks such as reverse shells through machine learning. Leveraging real-world threat intelligence and adversarial training, our framework synthesizes diverse malicious datasets while preserving the variability of legitimate activity, ensuring high accuracy and low false-positive rates. We validate our approach through extensive experiments on enterprise-scale datasets, achieving a 90\% improvement in detection rates over non-augmented baselines at an industry-grade False Positive Rate (FPR) of $10^{-5}$. We define black-box data-driven attacks that successfully evade unprotected models, and develop defenses to mitigate them, producing adversarially robust variants of ML models. Ethical considerations are central to this work; we discuss safeguards for synthetic data generation and the responsible release of pre-trained models across four best performing architectures, including both adversarially and regularly trained variants: https://huggingface.co/dtrizna/quasarnix. Furthermore, we provide a malicious LOTL dataset containing over 1 million augmented attack variants to enable reproducible research and community collaboration: https://huggingface.co/datasets/dtrizna/QuasarNix. This work offers a reproducible, scalable, and production-ready defense against evolving LOTL threats.

cs.CR↗

arXiv2024

Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions

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 test time. Although backdoor attacks have been demonstrated in a variety of settings and against different models, the factors affecting their effectiveness are still not well understood. In this work, we provide a unifying framework to study the process of backdoor learning under the lens of incremental learning and influence functions. We show that the effectiveness of backdoor attacks depends on: (i) the complexity of the learning algorithm, controlled by its hyperparameters; (ii) the fraction of backdoor samples injected into the training set; and (iii) the size and visibility of the backdoor trigger. These factors affect how fast a model learns to correlate the presence of the backdoor trigger with the target class. Our analysis unveils the intriguing existence of a region in the hyperparameter space in which the accuracy on clean test samples is still high while backdoor attacks are ineffective, thereby suggesting novel criteria to improve existing defenses.

cs.LG↗

arXiv2024

Nebula: Self-Attention for Dynamic Malware Analysis

Dynamic analysis enables detecting Windows malware by executing programs in a controlled environment and logging their actions. Previous work has proposed training machine learning models, i.e., convolutional and long short-term memory networks, on homogeneous input features like runtime APIs to either detect or classify malware, neglecting other relevant information coming from heterogeneous data like network and file operations. To overcome these issues, we introduce Nebula, a versatile, self-attention Transformer-based neural architecture that generalizes across different behavioral representations and formats, combining diverse information from dynamic log reports. Nebula is composed by several components needed to tokenize, filter, normalize and encode data to feed the transformer architecture. We firstly perform a comprehensive ablation study to evaluate their impact on the performance of the whole system, highlighting which components can be used as-is, and which must be enriched with specific domain knowledge. We perform extensive experiments on both malware detection and classification tasks, using three datasets acquired from different dynamic analyses platforms, show that, on average, Nebula outperforms state-of-the-art models at low false positive rates, with a peak of 12% improvement. Moreover, we showcase how self-supervised learning pre-training matches the performance of fully-supervised models with only 20% of training data, and we inspect the output of Nebula through explainable AI techniques, pinpointing how attention is focusing on specific tokens correlated to malicious activities of malware families. To foster reproducibility, we open-source our findings and models at https://github.com/dtrizna/nebula.

cs.CR↗

arXiv2024

Sonic: Fast and Transferable Data Poisoning on Clustering Algorithms

Data poisoning attacks on clustering algorithms have received limited attention, with existing methods struggling to scale efficiently as dataset sizes and feature counts increase. These attacks typically require re-clustering the entire dataset multiple times to generate predictions and assess the attacker's objectives, significantly hindering their scalability. This paper addresses these limitations by proposing Sonic, a novel genetic data poisoning attack that leverages incremental and scalable clustering algorithms, e.g., FISHDBC, as surrogates to accelerate poisoning attacks against graph-based and density-based clustering methods, such as HDBSCAN. We empirically demonstrate the effectiveness and efficiency of Sonic in poisoning the target clustering algorithms. We then conduct a comprehensive analysis of the factors affecting the scalability and transferability of poisoning attacks against clustering algorithms, and we conclude by examining the robustness of hyperparameters in our attack strategy Sonic.

cs.CR↗