Simone Milani

Ehsan Nowroozi, Yassine Mekdad, Mauro Conti et al.

Recently, the popularity and wide use of the last-generation video conferencing technologies created an exponential growth in its market size. Such technology allows participants in different geographic regions to have a virtual face-to-face meeting. Additionally, it enables users to employ a virtual background to conceal their own environment due to privacy concerns or to reduce distractions, particularly in professional settings. Nevertheless, in scenarios where the users should not hide their actual locations, they may mislead other participants by claiming their virtual background as a real one. Therefore, it is crucial to develop tools and strategies to detect the authenticity of the considered virtual background. In this paper, we present a detection strategy to distinguish between real and virtual video conferencing user backgrounds. We demonstrate that our detector is robust against two attack scenarios. The first scenario considers the case where the detector is unaware about the attacks and inn the second scenario, we make the detector aware of the adversarial attacks, which we refer to Adversarial Multimedia Forensics (i.e, the forensically-edited frames are included in the training set). Given the lack of publicly available dataset of virtual and real backgrounds for video conferencing, we created our own dataset and made them publicly available [1]. Then, we demonstrate the robustness of our detector against different adversarial attacks that the adversary considers. Ultimately, our detector's performance is significant against the CRSPAM1372 [2] features, and post-processing operations such as geometric transformations with different quality factors that the attacker may choose. Moreover, our performance results shows that we can perfectly identify a real from a virtual background with an accuracy of 99.80%.

Francesco Barbato, Elena Camuffo, Simone Milani et al.

State-of-the-art multimodal semantic segmentation strategies combining LiDAR and color data are usually designed on top of asymmetric information-sharing schemes and assume that both modalities are always available. This strong assumption may not hold in real-world scenarios, where sensors are prone to failure or can face adverse conditions that make the acquired information unreliable. This problem is exacerbated when continual learning scenarios are considered since they have stringent data reliability constraints. In this work, we re-frame the task of multimodal semantic segmentation by enforcing a tightly coupled feature representation and a symmetric information-sharing scheme, which allows our approach to work even when one of the input modalities is missing. We also introduce an ad-hoc class-incremental continual learning scheme, proving our approach's effectiveness and reliability even in safety-critical settings, such as autonomous driving. We evaluate our approach on the SemanticKITTI dataset, achieving impressive performances.

Daniele Mari, Davide Salvi, Paolo Bestagini et al.

Recent advances in deep learning and computer vision have made the synthesis and counterfeiting of multimedia content more accessible than ever, leading to possible threats and dangers from malicious users. In the audio field, we are witnessing the growth of speech deepfake generation techniques, which solicit the development of synthetic speech detection algorithms to counter possible mischievous uses such as frauds or identity thefts. In this paper, we consider three different feature sets proposed in the literature for the synthetic speech detection task and present a model that fuses them, achieving overall better performances with respect to the state-of-the-art solutions. The system was tested on different scenarios and datasets to prove its robustness to anti-forensic attacks and its generalization capabilities.

Daniele Mari, Federica Latora, Simone Milani

The recent integration of generative neural strategies and audio processing techniques have fostered the widespread of synthetic speech synthesis or transformation algorithms. This capability proves to be harmful in many legal and informative processes (news, biometric authentication, audio evidence in courts, etc.). Thus, the development of efficient detection algorithms is both crucial and challenging due to the heterogeneity of forgery techniques. This work investigates the discriminative role of silenced parts in synthetic speech detection and shows how first digit statistics extracted from MFCC coefficients can efficiently enable a robust detection. The proposed procedure is computationally-lightweight and effective on many different algorithms since it does not rely on large neural detection architecture and obtains an accuracy above 90\% in most of the classes of the ASVSpoof dataset.

Elena Camuffo, Simone Milani

During the last few years, continual learning (CL) strategies for image classification and segmentation have been widely investigated designing innovative solutions to tackle catastrophic forgetting, like knowledge distillation and self-inpainting. However, the application of continual learning paradigms to point clouds is still unexplored and investigation is required, especially using architectures that capture the sparsity and uneven distribution of LiDAR data. The current paper analyzes the problem of class incremental learning applied to point cloud semantic segmentation, comparing approaches and state-of-the-art architectures. To the best of our knowledge, this is the first example of class-incremental continual learning for LiDAR point cloud semantic segmentation. Different CL strategies were adapted to LiDAR point clouds and tested, tackling both classic fine-tuning scenarios and the Coarse-to-Fine learning paradigm. The framework has been evaluated through two different architectures on SemanticKITTI, obtaining results in line with state-of-the-art CL strategies and standard offline learning.

Elena Camuffo, Umberto Michieli, Simone Milani

Recent advances in autonomous robotic technologies have highlighted the growing need for precise environmental analysis. LiDAR semantic segmentation has gained attention to accomplish fine-grained scene understanding by acting directly on raw content provided by sensors. Recent solutions showed how different learning techniques can be used to improve the performance of the model, without any architectural or dataset change. Following this trend, we present a coarse-to-fine setup that LEArns from classification mistaKes (LEAK) derived from a standard model. First, classes are clustered into macro groups according to mutual prediction errors; then, the learning process is regularized by: (1) aligning class-conditional prototypical feature representation for both fine and coarse classes, (2) weighting instances with a per-class fairness index. Our LEAK approach is very general and can be seamlessly applied on top of any segmentation architecture; indeed, experimental results showed that it enables state-of-the-art performances on different architectures, datasets and tasks, while ensuring more balanced class-wise results and faster convergence.

Elena Camuffo, Umberto Michieli, Simone Milani et al.

Developing a reliable vision system is a fundamental challenge for robotic technologies (e.g., indoor service robots and outdoor autonomous robots) which can ensure reliable navigation even in challenging environments such as adverse weather conditions (e.g., fog, rain), poor lighting conditions (e.g., over/under exposure), or sensor degradation (e.g., blurring, noise), and can guarantee high performance in safety-critical functions. Current solutions proposed to improve model robustness usually rely on generic data augmentation techniques or employ costly test-time adaptation methods. In addition, most approaches focus on addressing a single vision task (typically, image recognition) utilising synthetic data. In this paper, we introduce Per-corruption Adaptation of Normalization statistics (PAN) to enhance the model robustness of vision systems. Our approach entails three key components: (i) a corruption type identification module, (ii) dynamic adjustment of normalization layer statistics based on identified corruption type, and (iii) real-time update of these statistics according to input data. PAN can integrate seamlessly with any convolutional model for enhanced accuracy in several robot vision tasks. In our experiments, PAN obtains robust performance improvement on challenging real-world corrupted image datasets (e.g., OpenLoris, ExDark, ACDC), where most of the current solutions tend to fail. Moreover, PAN outperforms the baseline models by 20-30% on synthetic benchmarks in object recognition tasks.

Daniele Mari, Saverio Cavasin, Simone Milani et al.

The success of learning-based coding techniques and the development of learning-based image coding standards, such as JPEG-AI, point towards the adoption of such solutions in different fields, including the storage of biometric data, like fingerprints. However, the peculiar nature of learning-based compression artifacts poses several issues concerning their impact and effectiveness on extracting biometric features and landmarks, e.g., minutiae. This problem is utterly stressed by the fact that most models are trained on natural color images, whose characteristics are very different from usual biometric images, e.g, fingerprint or iris pictures. As a matter of fact, these issues are deemed to be accurately questioned and investigated, being such analysis still largely unexplored. This study represents the first investigation about the adaptability of learning-based image codecs in the storage of fingerprint images by measuring its impact on the extraction and characterization of minutiae. Experimental results show that at a fixed rate point, learned solutions considerably outperform previous fingerprint coding standards, like JPEG2000, both in terms of distortion and minutiae preservation. Indeed, experimental results prove that the peculiarities of learned compression artifacts do not prevent automatic fingerprint identification (since minutiae types and locations are not significantly altered), nor do compromise image quality for human visual inspection (as they gain in terms of BD rate and PSNR of 47.8% and +3.97dB respectively).

Daniele Mari, Simone Milani

Learned image compression codecs have recently achieved impressive compression performances surpassing the most efficient image coding architectures. However, most approaches are trained to minimize rate and distortion which often leads to unsatisfactory visual results at low bitrates since perceptual metrics are not taken into account. In this paper, we show that conditional diffusion models can lead to promising results in the generative compression task when used as a decoder, and that, given a compressed representation, they allow creating new tradeoff points between distortion and perception at the decoder side based on the sampling method.

Chiara Schiavo, Elena Camuffo, Leonardo Badia et al.

3D Gaussian Splatting (3DGS) has significantly improved the efficiency and realism of three-dimensional scene visualization in several applications, ranging from robotics to eXtended Reality (XR). This work presents SAGE (Semantic-Driven Adaptive Gaussian Splatting in Extended Reality), a novel framework designed to enhance the user experience by dynamically adapting the Level of Detail (LOD) of different 3DGS objects identified via a semantic segmentation. Experimental results demonstrate how SAGE effectively reduces memory and computational overhead while keeping a desired target visual quality, thus providing a powerful optimization for interactive XR applications.

Daniele Mari, André F. R. Guarda, Nuno M. M. Rodrigues et al.

The widespread usage of point clouds (PC) for immersive visual applications has resulted in the use of very heterogeneous receiving conditions and devices, notably in terms of network, hardware, and display capabilities. In this scenario, quality scalability, i.e., the ability to reconstruct a signal at different qualities by progressively decoding a single bitstream, is a major requirement that has yet to be conveniently addressed, notably in most learning-based PC coding solutions. This paper proposes a quality scalability scheme, named Scalable Quality Hyperprior (SQH), adaptable to learning-based static point cloud geometry codecs, which uses a Quality-conditioned Latents Probability Estimator (QuLPE) to decode a high-quality version of a PC learning-based representation, based on an available lower quality base layer. SQH is integrated in the future JPEG PC coding standard, allowing to create a layered bitstream that can be used to progressively decode the PC geometry with increasing quality and fidelity. Experimental results show that SQH offers the quality scalability feature with very limited or no compression performance penalty at all when compared with the corresponding non-scalable solution, thus preserving the significant compression gains over other state-of-the-art PC codecs.

Elena Camuffo, Francesco Barbato, Mete Ozay et al.

We introduce MOCHA (Multi-modal Objects-aware Cross-arcHitecture Alignment), a knowledge distillation approach that transfers region-level multimodal semantics from a large vision-language teacher (e.g., LLaVa) into a lightweight vision-only object detector student (e.g., YOLO). A translation module maps student features into a joint space, where the training of the student and translator is guided by a dual-objective loss that enforces both local alignment and global relational consistency. Unlike prior approaches focused on dense or global alignment, MOCHA operates at the object level, enabling efficient transfer of semantics without modifying the teacher or requiring textual input at inference. We validate our method across four personalized detection benchmarks under few-shot regimes. Results show consistent gains over baselines, with a +10.1 average score improvement. Despite its compact architecture, MOCHA reaches performance on par with larger multimodal models, proving its suitability for real-world deployment.

Saverio Cavasin, Pietro Biasetton, Mattia Tamiazzo et al.

During criminal investigations, images of persons of interest directly influence the success of identification procedures. However, law enforcement agencies often face challenges related to the scarcity of high-quality images or their obsolescence, which can affect the accuracy and success of people searching processes. This paper introduces a novel forensic mugshot augmentation framework aimed at addressing these limitations. Our approach enhances the identification probability of individuals by generating additional, high-quality images through customizable data augmentation techniques, while maintaining the biometric integrity and consistency of the original data. Several experimental results show that our method significantly improves identification accuracy and robustness across various forensic scenarios, demonstrating its effectiveness as a trustworthy tool law enforcement applications. Index Terms: Digital Forensics, Person re-identification, Feature extraction, Data augmentation, Visual-Language models.

Daniele Mari, André F. R. Guarda, Nuno M. M. Rodrigues et al.

In the current age, users consume multimedia content in very heterogeneous scenarios in terms of network, hardware, and display capabilities. A naive solution to this problem is to encode multiple independent streams, each covering a different possible requirement for the clients, with an obvious negative impact in both storage and computational requirements. These drawbacks can be avoided by using codecs that enable scalability, i.e., the ability to generate a progressive bitstream, containing a base layer followed by multiple enhancement layers, that allow decoding the same bitstream serving multiple reconstructions and visualization specifications. While scalable coding is a well-known and addressed feature in conventional image and video codecs, this paper focuses on a new and very different problem, notably the development of scalable coding solutions for deep learning-based Point Cloud (PC) coding. The peculiarities of this 3D representation make it hard to implement flexible solutions that do not compromise the other functionalities of the codec. This paper proposes a joint quality and resolution scalability scheme, named Scalable Resolution and Quality Hyperprior (SRQH), that, contrary to previous solutions, can model the relationship between latents obtained with models trained for different RD tradeoffs and/or at different resolutions. Experimental results obtained by integrating SRQH in the emerging JPEG Pleno learning-based PC coding standard show that SRQH allows decoding the PC at different qualities and resolutions with a single bitstream while incurring only in a limited RD penalty and increment in complexity w.r.t. non-scalable JPEG PCC that would require one bitstream per coding configuration.

Saverio Cavasin, Daniele Mari, Simone Milani et al.

Generative models are gaining significant attention as potential catalysts for a novel industrial revolution. Since automated sample generation can be useful to solve privacy and data scarcity issues that usually affect learned biometric models, such technologies became widely spread in this field. In this paper, we assess the vulnerabilities of generative machine learning models concerning identity protection by designing and testing an identity inference attack on fingerprint datasets created by means of a generative adversarial network. Experimental results show that the proposed solution proves to be effective under different configurations and easily extendable to other biometric measurements.

Matteo Cardaioli, Stefano Cecconello, Mauro Conti et al.

Automated Teller Machines (ATMs) represent the most used system for withdrawing cash. The European Central Bank reported more than 11 billion cash withdrawals and loading/unloading transactions on the European ATMs in 2019. Although ATMs have undergone various technological evolutions, Personal Identification Numbers (PINs) are still the most common authentication method for these devices. Unfortunately, the PIN mechanism is vulnerable to shoulder-surfing attacks performed via hidden cameras installed near the ATM to catch the PIN pad. To overcome this problem, people get used to covering the typing hand with the other hand. While such users probably believe this behavior is safe enough to protect against mentioned attacks, there is no clear assessment of this countermeasure in the scientific literature. This paper proposes a novel attack to reconstruct PINs entered by victims covering the typing hand with the other hand. We consider the setting where the attacker can access an ATM PIN pad of the same brand/model as the target one. Afterward, the attacker uses that model to infer the digits pressed by the victim while entering the PIN. Our attack owes its success to a carefully selected deep learning architecture that can infer the PIN from the typing hand position and movements. We run a detailed experimental analysis including 58 users. With our approach, we can guess 30% of the 5-digit PINs within three attempts -- the ones usually allowed by ATM before blocking the card. We also conducted a survey with 78 users that managed to reach an accuracy of only 7.92% on average for the same setting. Finally, we evaluate a shielding countermeasure that proved to be rather inefficient unless the whole keypad is shielded.

Mauro Conti, Simone Milani, Ehsan Nowroozi et al.

The last-generation video conferencing software allows users to utilize a virtual background to conceal their personal environment due to privacy concerns, especially in official meetings with other employers. On the other hand, users maybe want to fool people in the meeting by considering the virtual background to conceal where they are. In this case, developing tools to understand the virtual background utilize for fooling people in meeting plays an important role. Besides, such detectors must prove robust against different kinds of attacks since a malicious user can fool the detector by applying a set of adversarial editing steps on the video to conceal any revealing footprint. In this paper, we study the feasibility of an efficient tool to detect whether a videoconferencing user background is real. In particular, we provide the first tool which computes pixel co-occurrences matrices and uses them to search for inconsistencies among spectral and spatial bands. Our experiments confirm that cross co-occurrences matrices improve the robustness of the detector against different kinds of attacks. This work's performance is especially noteworthy with regard to color SPAM features. Moreover, the performance especially is significant with regard to robustness versus post-processing, like geometric transformations, filtering, contrast enhancement, and JPEG compression with different quality factors.

Sebastiano Verde, Paolo Bestagini, Simone Milani et al.

Forgery operations on video contents are nowadays within the reach of anyone, thanks to the availability of powerful and user-friendly editing software. Integrity verification and authentication of videos represent a major interest in both journalism (e.g., fake news debunking) and legal environments dealing with digital evidence (e.g., a court of law). While several strategies and different forensics traces have been proposed in recent years, latest solutions aim at increasing the accuracy by combining multiple detectors and features. This paper presents a video forgery localization framework that verifies the self-consistency of coding traces between and within video frames, by fusing the information derived from a set of independent feature descriptors. The feature extraction step is carried out by means of an explainable convolutional neural network architecture, specifically designed to look for and classify coding artifacts. The overall framework was validated in two typical forgery scenarios: temporal and spatial splicing. Experimental results show an improvement to the state-of-the-art on temporal splicing localization and also promising performance in the newly tackled case of spatial splicing, on both synthetic and real-world videos.

Nicolò Bonettini, Paolo Bestagini, Simone Milani et al.

The advent of Generative Adversarial Network (GAN) architectures has given anyone the ability of generating incredibly realistic synthetic imagery. The malicious diffusion of GAN-generated images may lead to serious social and political consequences (e.g., fake news spreading, opinion formation, etc.). It is therefore important to regulate the widespread distribution of synthetic imagery by developing solutions able to detect them. In this paper, we study the possibility of using Benford's law to discriminate GAN-generated images from natural photographs. Benford's law describes the distribution of the most significant digit for quantized Discrete Cosine Transform (DCT) coefficients. Extending and generalizing this property, we show that it is possible to extract a compact feature vector from an image. This feature vector can be fed to an extremely simple classifier for GAN-generated image detection purpose.

Riccardo Bonetto, Mattia Soldan, Alberto Lanaro et al.

Smartphones and wearable devices are fast growing technologies that, in conjunction with advances in wireless sensor hardware, are enabling ubiquitous sensing applications. Wearables are suitable for indoor and outdoor scenarios, can be placed on many parts of the human body and can integrate a large number of sensors capable of gathering physiological and behavioral biometric information. Here, we are concerned with gait analysis systems that extract meaningful information from a user's movements to identify anomalies and changes in their walking style. The solution that is put forward is subject-specific, as the designed feature extraction and classification tools are trained on the subject under observation. A smartphone mounted on an ad-hoc made chest support is utilized to gather inertial data and video signals from its built-in sensors and rear-facing camera. The collected video and inertial data are preprocessed, combined and then classified by means of a Recurrent Neural Network (RNN) based Sequence-to-Sequence (Seq2Seq) model, which is used as a feature extractor, and a following Convolutional Neural Network (CNN) classifier. This architecture provides excellent results, being able to correctly assess anomalies in 100% of the cases, for the considered tests, surpassing the performance of support vector machine classifiers.