arXiv subjects

Sara Rampazzi

Publications and source records attributed to Sara Rampazzi.

15 recordsLinked to original sources

arXiv2025

Active Localization of Close-range Adversarial Acoustic Sources for Underwater Data Center Surveillance

Underwater data infrastructures offer natural cooling and enhanced physical security compared to terrestrial facilities, but their storage systems remain susceptible to acoustic injection attacks, where sound-induced mechanical vibrations disrupt critical I/O operations and compromise data availability. This work presents a surveillance framework for localizing and tracking such close-range adversarial acoustic sources targeting offshore infrastructures, particularly underwater data centers (UDCs). We propose a scalable heterogeneous receiver configuration with one facility-mounted hydrophone and one mobile hydrophone carried by a surveillance robot. The resulting problem differs from conventional sound source localization (SSL) due to distributed facility scale, narrowband signaling with phase ambiguity, non-cooperative sources, and mobile receiver state uncertainty. To address these challenges, we formulate a Locus-Conditioned Maximum A-Posteriori (LC-MAP) scheme that generates acoustically informed priors, ensuring a physically plausible initial state for a joint time- and frequency-difference-of-arrival (TDOA-FDOA) filtering. We integrate this into an unscented Kalman filter (UKF) pipeline, along with a multipath-aware measurement model that compensates for surface and bed reflections, and an effective measurement covariance that accounts for mobile receiver uncertainty. Extensive Monte Carlo analyses, fixed-array baseline comparisons, Gazebo-based physics simulations, and field trials demonstrate reliable real-time localization and tracking. The framework achieves sub-meter localization accuracy and over 90% success rates in most scenarios, with convergence times nearly halved compared to baselines. Overall, this study establishes a geometry-aware, real-time approach for acoustic threat localization and advances autonomous surveillance capabilities of underwater infrastructure.

eess.SP↗

arXiv2025

FACE: Faithful Automatic Concept Extraction

Interpreting deep neural networks through concept-based explanations offers a bridge between low-level features and high-level human-understandable semantics. However, existing automatic concept discovery methods often fail to align these extracted concepts with the model's true decision-making process, thereby compromising explanation faithfulness. In this work, we propose FACE (Faithful Automatic Concept Extraction), a novel framework that augments Non-negative Matrix Factorization (NMF) with a Kullback-Leibler (KL) divergence regularization term to ensure alignment between the model's original and concept-based predictions. Unlike prior methods that operate solely on encoder activations, FACE incorporates classifier supervision during concept learning, enforcing predictive consistency and enabling faithful explanations. We provide theoretical guarantees showing that minimizing the KL divergence bounds the deviation in predictive distributions, thereby promoting faithful local linearity in the learned concept space. Systematic evaluations on ImageNet, COCO, and CelebA datasets demonstrate that FACE outperforms existing methods across faithfulness and sparsity metrics.

cs.CV↗

arXiv2024

The Elephant in the Room: Software and Hardware Security Vulnerabilities of Portable Sequencing Devices

Portable genome sequencing technology is revolutionizing genomic research by providing a faster, more flexible method of sequencing DNA and RNA [1, 2]. The unprecedented shift from bulky stand-alone benchtop equipment confined in a laboratory setting to small portable devices which can be easily carried anywhere outside the laboratory network and connected to untrusted external computers to perform sequencing raises new security and privacy threats not considered before. Current research primarily addresses the privacy of DNA/RNA data in online databases [3] and the security of stand-alone sequencing devices such as Illumina [4]. However, it overlooks the security risks arising from compromises of computer devices directly connected to portable sequencers as illustrated in Fig. 1. While highly sensitive data, such as the human genome, has become easier to sequence, the networks connecting to these smaller devices and the hardware running basecalling can no longer implicitly be trusted, and doing so can deteriorate the confidentiality and integrity of the genomic data being processed. Here, we present new security and privacy threats of portable sequencing technology and recommendations to aid in ensuring sequencing data is kept private and secure. First, to prevent unauthorized access to sequencing devices, IP addresses should not be considered a sufficient authentication mechanism. Second, integrity checks are necessary for all data passed from the sequencer to external computers to avoid data manipulation. Finally, encryption should be considered as data is passed from the sequencer to such external computers to prevent eavesdropping on data as it is sent and stored. As devices and technology rapidly change, it becomes paramount to reevaluate security requirements alongside them or risk leaving some of our most sensitive data exposed.

cs.CR↗

arXiv2024

AquaSonic: Acoustic Manipulation of Underwater Data Center Operations and Resource Management

Underwater datacenters (UDCs) hold promise as next-generation data storage due to their energy efficiency and environmental sustainability benefits. While the natural cooling properties of water save power, the isolated aquatic environment and long-range sound propagation in water create unique vulnerabilities which differ from those of on-land data centers. Our research discovers the unique vulnerabilities of fault-tolerant storage devices, resource allocation software, and distributed file systems to acoustic injection attacks in UDCs. With a realistic testbed approximating UDC server operations, we empirically characterize the capabilities of acoustic injection underwater and find that an attacker can reduce fault-tolerant RAID 5 storage system throughput by 17% up to 100%. Our closed-water analyses reveal that attackers can (i) cause unresponsiveness and automatic node removal in a distributed filesystem with only 2.4 minutes of sustained acoustic injection, (ii) induce a distributed database's latency to increase by up to 92.7% to reduce system reliability, and (iii) induce load-balance managers to redirect up to 74% of resources to a target server to cause overload or force resource colocation. Furthermore, we perform open-water experiments in a lake and find that an attacker can cause controlled throughput degradation at a maximum allowable distance of 6.35 m using a commercial speaker. We also investigate and discuss the effectiveness of standard defenses against acoustic injection attacks. Finally, we formulate a novel machine learning-based detection system that reaches 0% False Positive Rate and 98.2% True Positive Rate trained on our dataset of profiled hard disk drives under 30-second FIO benchmark execution. With this work, we aim to help manufacturers proactively protect UDCs against acoustic injection attacks and ensure the security of subsea computing infrastructures.

cs.CR↗

arXiv2024

PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysis

Deep neural networks for classification are vulnerable to adversarial attacks, where small perturbations to input samples lead to incorrect predictions. This susceptibility, combined with the black-box nature of such networks, limits their adoption in critical applications like autonomous driving. Feature-attribution-based explanation methods provide relevance of input features for model predictions on input samples, thus explaining model decisions. However, we observe that both model predictions and feature attributions for input samples are sensitive to noise. We develop a practical method for this characteristic of model prediction and feature attribution to detect adversarial samples. Our method, PASA, requires the computation of two test statistics using model prediction and feature attribution and can reliably detect adversarial samples using thresholds learned from benign samples. We validate our lightweight approach by evaluating the performance of PASA on varying strengths of FGSM, PGD, BIM, and CW attacks on multiple image and non-image datasets. On average, we outperform state-of-the-art statistical unsupervised adversarial detectors on CIFAR-10 and ImageNet by 14\% and 35\% ROC-AUC scores, respectively. Moreover, our approach demonstrates competitive performance even when an adversary is aware of the defense mechanism.

cs.CR↗

arXiv2024

Invisible Reflections: Leveraging Infrared Laser Reflections to Target Traffic Sign Perception

All vehicles must follow the rules that govern traffic behavior, regardless of whether the vehicles are human-driven or Connected Autonomous Vehicles (CAVs). Road signs indicate locally active rules, such as speed limits and requirements to yield or stop. Recent research has demonstrated attacks, such as adding stickers or projected colored patches to signs, that cause CAV misinterpretation, resulting in potential safety issues. Humans can see and potentially defend against these attacks. But humans can not detect what they can not observe. We have developed an effective physical-world attack that leverages the sensitivity of filterless image sensors and the properties of Infrared Laser Reflections (ILRs), which are invisible to humans. The attack is designed to affect CAV cameras and perception, undermining traffic sign recognition by inducing misclassification. In this work, we formulate the threat model and requirements for an ILR-based traffic sign perception attack to succeed. We evaluate the effectiveness of the ILR attack with real-world experiments against two major traffic sign recognition architectures on four IR-sensitive cameras. Our black-box optimization methodology allows the attack to achieve up to a 100% attack success rate in indoor, static scenarios and a >80.5% attack success rate in our outdoor, moving vehicle scenarios. We find the latest state-of-the-art certifiable defense is ineffective against ILR attacks as it mis-certifies >33.5% of cases. To address this, we propose a detection strategy based on the physical properties of IR laser reflections which can detect 96% of ILR attacks.

cs.CR↗

arXiv2023

SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability

Interpretability, trustworthiness, and usability are key considerations in high-stake security applications, especially when utilizing deep learning models. While these models are known for their high accuracy, they behave as black boxes in which identifying important features and factors that led to a classification or a prediction is difficult. This can lead to uncertainty and distrust, especially when an incorrect prediction results in severe consequences. Thus, explanation methods aim to provide insights into the inner working of deep learning models. However, most explanation methods provide inconsistent explanations, have low fidelity, and are susceptible to adversarial manipulation, which can reduce model trustworthiness. This paper provides a comprehensive analysis of explainable methods and demonstrates their efficacy in three distinct security applications: anomaly detection using system logs, malware prediction, and detection of adversarial images. Our quantitative and qualitative analysis reveals serious limitations and concerns in state-of-the-art explanation methods in all three applications. We show that explanation methods for security applications necessitate distinct characteristics, such as stability, fidelity, robustness, and usability, among others, which we outline as the prerequisites for trustworthy explanation methods.

cs.CR↗

arXiv2023

Side Eye: Characterizing the Limits of POV Acoustic Eavesdropping from Smartphone Cameras with Rolling Shutters and Movable Lenses

Our research discovers how the rolling shutter and movable lens structures widely found in smartphone cameras modulate structure-borne sounds onto camera images, creating a point-of-view (POV) optical-acoustic side channel for acoustic eavesdropping. The movement of smartphone camera hardware leaks acoustic information because images unwittingly modulate ambient sound as imperceptible distortions. Our experiments find that the side channel is further amplified by intrinsic behaviors of Complementary metal-oxide-semiconductor (CMOS) rolling shutters and movable lenses such as in Optical Image Stabilization (OIS) and Auto Focus (AF). Our paper characterizes the limits of acoustic information leakage caused by structure-borne sound that perturbs the POV of smartphone cameras. In contrast with traditional optical-acoustic eavesdropping on vibrating objects, this side channel requires no line of sight and no object within the camera's field of view (images of a ceiling suffice). Our experiments test the limits of this side channel with a novel signal processing pipeline that extracts and recognizes the leaked acoustic information. Our evaluation with 10 smartphones on a spoken digit dataset reports 80.66%, 91.28%, and 99.67% accuracies on recognizing 10 spoken digits, 20 speakers, and 2 genders respectively. We further systematically discuss the possible defense strategies and implementations. By modeling, measuring, and demonstrating the limits of acoustic eavesdropping from smartphone camera image streams, our contributions explain the physics-based causality and possible ways to reduce the threat on current and future devices.

cs.CR↗

arXiv2022

You Can't See Me: Physical Removal Attacks on LiDAR-based Autonomous Vehicles Driving Frameworks

Autonomous Vehicles (AVs) increasingly use LiDAR-based object detection systems to perceive other vehicles and pedestrians on the road. While existing attacks on LiDAR-based autonomous driving architectures focus on lowering the confidence score of AV object detection models to induce obstacle misdetection, our research discovers how to leverage laser-based spoofing techniques to selectively remove the LiDAR point cloud data of genuine obstacles at the sensor level before being used as input to the AV perception. The ablation of this critical LiDAR information causes autonomous driving obstacle detectors to fail to identify and locate obstacles and, consequently, induces AVs to make dangerous automatic driving decisions. In this paper, we present a method invisible to the human eye that hides objects and deceives autonomous vehicles' obstacle detectors by exploiting inherent automatic transformation and filtering processes of LiDAR sensor data integrated with autonomous driving frameworks. We call such attacks Physical Removal Attacks (PRA), and we demonstrate their effectiveness against three popular AV obstacle detectors (Apollo, Autoware, PointPillars), and we achieve 45° attack capability. We evaluate the attack impact on three fusion models (Frustum-ConvNet, AVOD, and Integrated-Semantic Level Fusion) and the consequences on the driving decision using LGSVL, an industry-grade simulator. In our moving vehicle scenarios, we achieve a 92.7% success rate removing 90\% of a target obstacle's cloud points. Finally, we demonstrate the attack's success against two popular defenses against spoofing and object hiding attacks and discuss two enhanced defense strategies to mitigate our attack.

cs.CR↗

arXiv2022

A Practical Methodology for ML-Based EM Side Channel Disassemblers

Providing security guarantees for embedded devices with limited interface capabilities is an increasingly crucial task. Although these devices don't have traditional interfaces, they still generate unintentional electromagnetic signals that correlate with the instructions being executed. By collecting these traces using our methodology and leveraging a random forest algorithm to develop a machine learning model, we built an EM side channel based instruction level disassembler. The disassembler was tested on an Arduino UNO board, yielding an accuracy of 88.69% instruction recognition for traces from twelve instructions captured at a single location in the device; this is an improvement compared to the 75.6% (for twenty instructions) reported in previous similar work.

cs.CR↗

arXiv2022

Towards Adversarial Control Loops in Sensor Attacks: A Case Study to Control the Kinematics and Actuation of Embedded Systems

Recent works investigated attacks on sensors by influencing analog sensor components with acoustic, light, and electromagnetic signals. Such attacks can have extensive security, reliability, and safety implications since many types of the targeted sensors are also widely used in critical process control, robotics, automation, and industrial control systems. While existing works advanced our understanding of the physical-level risks that are hidden from a digital-domain perspective, gaps exist in how the attack can be guided to achieve system-level control in real-time, continuous processes. This paper proposes an adversarial control loop-based approach for real-time attacks on control systems relying on sensors. We study how to utilize the system feedback extracted from physical-domain signals to guide the attacks. In the attack process, injection signals are adjusted in real time based on the extracted feedback to exert targeted influence on a victim control system that is continuously affected by the injected perturbations and applying changes to the physical environment. In our case study, we investigate how an external adversarial control system can be constructed over sensor-actuator systems and demonstrate the attacks with program-controlled processes to manipulate the victim system without accessing its internal statuses.

cs.CR↗

arXiv2022

Explaining RADAR features for detecting spoofing attacks in Connected Autonomous Vehicles

Connected autonomous vehicles (CAVs) are anticipated to have built-in AI systems for defending against cyberattacks. Machine learning (ML) models form the basis of many such AI systems. These models are notorious for acting like black boxes, transforming inputs into solutions with great accuracy, but no explanations support their decisions. Explanations are needed to communicate model performance, make decisions transparent, and establish trust in the models with stakeholders. Explanations can also indicate when humans must take control, for instance, when the ML model makes low confidence decisions or offers multiple or ambiguous alternatives. Explanations also provide evidence for post-incident forensic analysis. Research on explainable ML to security problems is limited, and more so concerning CAVs. This paper surfaces a critical yet under-researched sensor data \textit{uncertainty} problem for training ML attack detection models, especially in highly mobile and risk-averse platforms such as autonomous vehicles. We present a model that explains \textit{certainty} and \textit{uncertainty} in sensor input -- a missing characteristic in data collection. We hypothesize that model explanation is inaccurate for a given system without explainable input data quality. We estimate \textit{uncertainty} and mass functions for features in radar sensor data and incorporate them into the training model through experimental evaluation. The mass function allows the classifier to categorize all spoofed inputs accurately with an incorrect class label.

cs.CR↗

arXiv2020

Light Commands: Laser-Based Audio Injection Attacks on Voice-Controllable Systems

We propose a new class of signal injection attacks on microphones by physically converting light to sound. We show how an attacker can inject arbitrary audio signals to a target microphone by aiming an amplitude-modulated light at the microphone's aperture. We then proceed to show how this effect leads to a remote voice-command injection attack on voice-controllable systems. Examining various products that use Amazon's Alexa, Apple's Siri, Facebook's Portal, and Google Assistant, we show how to use light to obtain control over these devices at distances up to 110 meters and from two separate buildings. Next, we show that user authentication on these devices is often lacking, allowing the attacker to use light-injected voice commands to unlock the target's smartlock-protected front doors, open garage doors, shop on e-commerce websites at the target's expense, or even unlock and start various vehicles connected to the target's Google account (e.g., Tesla and Ford). Finally, we conclude with possible software and hardware defenses against our attacks.

cs.CR↗

arXiv2019

Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving

In Autonomous Vehicles (AVs), one fundamental pillar is perception, which leverages sensors like cameras and LiDARs (Light Detection and Ranging) to understand the driving environment. Due to its direct impact on road safety, multiple prior efforts have been made to study its the security of perception systems. In contrast to prior work that concentrates on camera-based perception, in this work we perform the first security study of LiDAR-based perception in AV settings, which is highly important but unexplored. We consider LiDAR spoofing attacks as the threat model and set the attack goal as spoofing obstacles close to the front of a victim AV. We find that blindly applying LiDAR spoofing is insufficient to achieve this goal due to the machine learning-based object detection process. Thus, we then explore the possibility of strategically controlling the spoofed attack to fool the machine learning model. We formulate this task as an optimization problem and design modeling methods for the input perturbation function and the objective function. We also identify the inherent limitations of directly solving the problem using optimization and design an algorithm that combines optimization and global sampling, which improves the attack success rates to around 75%. As a case study to understand the attack impact at the AV driving decision level, we construct and evaluate two attack scenarios that may damage road safety and mobility. We also discuss defense directions at the AV system, sensor, and machine learning model levels.

cs.CR↗

arXiv2019

Trick or Heat? Manipulating Critical Temperature-Based Control Systems Using Rectification Attacks

Temperature sensing and control systems are widely used in the closed-loop control of critical processes such as maintaining the thermal stability of patients, or in alarm systems for detecting temperature-related hazards. However, the security of these systems has yet to be completely explored, leaving potential attack surfaces that can be exploited to take control over critical systems. In this paper we investigate the reliability of temperature-based control systems from a security and safety perspective. We show how unexpected consequences and safety risks can be induced by physical-level attacks on analog temperature sensing components. For instance, we demonstrate that an adversary could remotely manipulate the temperature sensor measurements of an infant incubator to cause potential safety issues, without tampering with the victim system or triggering automatic temperature alarms. This attack exploits the unintended rectification effect that can be induced in operational and instrumentation amplifiers to control the sensor output, tricking the internal control loop of the victim system to heat up or cool down. Furthermore, we show how the exploit of this hardware-level vulnerability could affect different classes of analog sensors that share similar signal conditioning processes. Our experimental results indicate that conventional defenses commonly deployed in these systems are not sufficient to mitigate the threat, so we propose a prototype design of a low-cost anomaly detector for critical applications to ensure the integrity of temperature sensor signals.

cs.CR↗