arXiv subjects

Soteris Demetriou

Publications and source records attributed to Soteris Demetriou.

At least 19 recordsLinked to original sources

arXiv2026

Explainability-Aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors

The structural vulnerabilities of point cloud-based 3D object detectors remain poorly understood. Prior work has studied adversarial robustness primarily on isolated 3D object models, while recent LiDAR spoofing attacks target richer and more realistic driving scenes but focus mainly on physical realizability rather than understanding detector behavior or attack efficiency. In this work, we investigate how LiDAR-based detectors rely on spatial evidence in complex scenes and whether these reliance patterns can be exploited to induce failures more efficiently. To this end, we propose an explainability-guided adversarial analysis methodology. We introduce the Saliency-LiDAR (SALL) method, which aggregates Integrated Gradient attributions across scenes to produce universal saliency maps for LiDAR-based 3D object detectors. Guided by these maps, we design the Explainability-aware Frustum Attack (EFA), which selectively perturbs only the most influential frustums rather than uniformly attacking entire object regions. Experiments on KITTI and nuScenes, across detectors such as PointPillars and SECOND, show that EFA reduces detection recall by more than 15 percentage points while requiring 25-50% fewer perturbed frustums than the state-of-the-art non-saliency-aware baseline. These findings reveal that modern 3D detectors concentrate discriminative evidence in a small subset of spatial regions, exposing a structural robustness vulnerability in current LiDAR perception systems. Our code is released at https://github.com/SecMindLab/Saliency_LiDAR.

cs.CV↗

arXiv2026

Selective Fine-Tuning for Targeted and Robust Concept Unlearning

Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods aim at reducing the models' likelihood of generating harmful content. Traditionally, this has been tackled at an individual concept level, with only a handful of recent works considering more realistic concept combinations. However, state of the art methods depend on full finetuning, which is computationally expensive. Concept localisation methods can facilitate selective finetuning, but existing techniques are static, resulting in suboptimal utility. In order to tackle these challenges, we propose TRUST (Targeted Robust Selective fine Tuning), a novel approach for dynamically estimating target concept neurons and unlearning them through selective finetuning, empowered by a Hessian based regularization. We show experimentally, against a number of SOTA baselines, that TRUST is robust against adversarial prompts, preserves generation quality to a significant degree, and is also significantly faster than the SOTA. Our method achieves unlearning of not only individual concepts but also combinations of concepts and conditional concepts, without any specific regularization.

cs.AI↗

arXiv2025

Understanding Dementia Speech Alignment with Diffusion-Based Image Generation

Text-to-image models generate highly realistic images based on natural language descriptions and millions of users use them to create and share images online. While it is expected that such models can align input text and generated image in the same latent space little has been done to understand whether this alignment is possible between pathological speech and generated images. In this work, we examine the ability of such models to align dementia-related speech information with the generated images and develop methods to explain this alignment. Surprisingly, we found that dementia detection is possible from generated images alone achieving 75% accuracy on the ADReSS dataset. We then leverage explainability methods to show which parts of the language contribute to the detection.

cs.LG↗

arXiv2025

ClaritySpeech: Dementia Obfuscation in Speech

Dementia, a neurodegenerative disease, alters speech patterns, creating communication barriers and raising privacy concerns. Current speech technologies, such as automatic speech transcription (ASR), struggle with dementia and atypical speech, further challenging accessibility. This paper presents a novel dementia obfuscation in speech framework, ClaritySpeech, integrating ASR, text obfuscation, and zero-shot text-to-speech (TTS) to correct dementia-affected speech while preserving speaker identity in low-data environments without fine-tuning. Results show a 16% and 10% drop in mean F1 score across various adversarial settings and modalities (audio, text, fusion) for ADReSS and ADReSSo, respectively, maintaining 50% speaker similarity. We also find that our system improves WER (from 0.73 to 0.08 for ADReSS and 0.15 for ADReSSo) and speech quality from 1.65 to ~2.15, enhancing privacy and accessibility.

cs.CL↗

arXiv2024

DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speech

Dementia is a sensitive neurocognitive disorder affecting tens of millions of people worldwide and its cases are expected to triple by 2050. Alarmingly, recent advancements in dementia classification make it possible for adversaries to violate affected individuals' privacy and infer their sensitive condition from speech transcriptions. Existing obfuscation methods in text have never been applied for dementia and depend on the availability of large labeled datasets which are challenging to collect for sensitive medical attributes. In this work, we bridge this research gap and tackle the above issues by leveraging Large-Language-Models (LLMs) with diverse prompt designs (zero-shot, few-shot, and knowledge-based) to obfuscate dementia in speech transcripts. Our evaluation shows that LLMs are more effective dementia obfuscators compared to competing methods. However, they have billions of parameters which renders them hard to train, store and share, and they are also fragile suffering from hallucination, refusal and contradiction effects among others. To further mitigate these, we propose a novel method, DiDOTS. DiDOTS distills knowledge from LLMs using a teacher-student paradigm and parameter-efficient fine-tuning. DiDOTS has one order of magnitude fewer parameters compared to its teacher LLM and can be fine-tuned using three orders of magnitude less parameters compared to full fine-tuning. Our evaluation shows that compared to prior work DiDOTS retains the performance of LLMs achieving 1.3x and 2.2x improvement in privacy performance on two datasets, while humans rate it as better in preserving utility even when compared to state-of-the-art paraphrasing models.

cs.CL↗

arXiv2024

Prosody-Driven Privacy-Preserving Dementia Detection

Speaker embeddings extracted from voice recordings have been proven valuable for dementia detection. However, by their nature, these embeddings contain identifiable information which raises privacy concerns. In this work, we aim to anonymize embeddings while preserving the diagnostic utility for dementia detection. Previous studies rely on adversarial learning and models trained on the target attribute and struggle in limited-resource settings. We propose a novel approach that leverages domain knowledge to disentangle prosody features relevant to dementia from speaker embeddings without relying on a dementia classifier. Our experiments show the effectiveness of our approach in preserving speaker privacy (speaker recognition F1-score .01%) while maintaining high dementia detection score F1-score of 74% on the ADReSS dataset. Our results are also on par with a more constrained classifier-dependent system on ADReSSo (.01% and .66%), and have no impact on synthesized speech naturalness.

cs.SD↗

arXiv2024

Adversarial 3D Virtual Patches using Integrated Gradients

LiDAR sensors are widely used in autonomous vehicles to better perceive the environment. However, prior works have shown that LiDAR signals can be spoofed to hide real objects from 3D object detectors. This study explores the feasibility of reducing the required spoofing area through a novel object-hiding strategy based on virtual patches (VPs). We first manually design VPs (MVPs) and show that VP-focused attacks can achieve similar success rates with prior work but with a fraction of the required spoofing area. Then we design a framework Saliency-LiDAR (SALL), which can identify critical regions for LiDAR objects using Integrated Gradients. VPs crafted on critical regions (CVPs) reduce object detection recall by at least 15% compared to our baseline with an approximate 50% reduction in the spoofing area for vehicles of average size.

cs.CV↗

arXiv2024

Username Squatting on Online Social Networks: A Study on X

Adversaries have been targeting unique identifiers to launch typo-squatting, mobile app squatting and even voice squatting attacks. Anecdotal evidence suggest that online social networks (OSNs) are also plagued with accounts that use similar usernames. This can be confusing to users but can also be exploited by adversaries. However, to date no study characterizes this problem on OSNs. In this work, we define the username squatting problem and design the first multi-faceted measurement study to characterize it on X. We develop a username generation tool (UsernameCrazy) to help us analyze hundreds of thousands of username variants derived from celebrity accounts. Our study reveals that thousands of squatted usernames have been suspended by X, while tens of thousands that still exist on the network are likely bots. Out of these, a large number share similar profile pictures and profile names to the original account signalling impersonation attempts. We found that squatted accounts are being mentioned by mistake in tweets hundreds of thousands of times and are even being prioritized in searches by the network's search recommendation algorithm exacerbating the negative impact squatted accounts can have in OSNs. We use our insights and take the first step to address this issue by designing a framework (SQUAD) that combines UsernameCrazy with a new classifier to efficiently detect suspicious squatted accounts. Our evaluation of SQUAD's prototype implementation shows that it can achieve 94% F1-score when trained on a small dataset.

cs.CR↗

arXiv2022

Quantifying and Localizing Usable Information Leakage from Neural Network Gradients

In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent attacks show that one can still extract private information from the shared network's gradients compromising clients' privacy. In this paper, to quantify the private information leakage from gradients we adopt usable information theory. We focus on two types of private information: original information in data reconstruction attacks and latent information in attribute inference attacks. Furthermore, a sensitivity analysis over the gradients is performed to explore the underlying cause of information leakage and validate the results of the proposed framework. Finally, we conduct numerical evaluations on six benchmark datasets and four well-known deep models. We measure the impact of training hyperparameters, e.g., batches and epochs, as well as potential defense mechanisms, e.g., dropout and differential privacy. Our proposed framework enables clients to localize and quantify the private information leakage in a layer-wise manner, and enables a better understanding of the sources of information leakage in collaborative learning, which can be used by future studies to benchmark new attacks and defense mechanisms.

cs.LG↗

arXiv2022

Data Augmentation for Dementia Detection in Spoken Language

Dementia is a growing problem as our society ages, and detection methods are often invasive and expensive. Recent deep-learning techniques can offer a faster diagnosis and have shown promising results. However, they require large amounts of labelled data which is not easily available for the task of dementia detection. One effective solution to sparse data problems is data augmentation, though the exact methods need to be selected carefully. To date, there has been no empirical study of data augmentation on Alzheimer's disease (AD) datasets for NLP and speech processing. In this work, we investigate data augmentation techniques for the task of AD detection and perform an empirical evaluation of the different approaches on two kinds of models for both the text and audio domains. We use a transformer-based model for both domains, and SVM and Random Forest models for the text and audio domains, respectively. We generate additional samples using traditional as well as deep learning based methods and show that data augmentation improves performance for both the text- and audio-based models and that such results are comparable to state-of-the-art results on the popular ADReSS set, with carefully crafted architectures and features.

cs.CL↗

arXiv2022

Using 3D Shadows to Detect Object Hiding Attacks on Autonomous Vehicle Perception

Autonomous Vehicles (AVs) are mostly reliant on LiDAR sensors which enable spatial perception of their surroundings and help make driving decisions. Recent works demonstrated attacks that aim to hide objects from AV perception, which can result in severe consequences. 3D shadows, are regions void of measurements in 3D point clouds which arise from occlusions of objects in a scene. 3D shadows were proposed as a physical invariant valuable for detecting spoofed or fake objects. In this work, we leverage 3D shadows to locate obstacles that are hidden from object detectors. We achieve this by searching for void regions and locating the obstacles that cause these shadows. Our proposed methodology can be used to detect an object that has been hidden by an adversary as these objects, while hidden from 3D object detectors, still induce shadow artifacts in 3D point clouds, which we use for obstacle detection. We show that using 3D shadows for obstacle detection can achieve high accuracy in matching shadows to their object and provide precise prediction of an obstacle's distance from the ego-vehicle.

cs.CV↗

arXiv2021

Characterizing Improper Input Validation Vulnerabilities of Mobile Crowdsourcing Services

Mobile crowdsourcing services (MCS), enable fast and economical data acquisition at scale and find applications in a variety of domains. Prior work has shown that Foursquare and Waze (a location-based and a navigation MCS) are vulnerable to different kinds of data poisoning attacks. Such attacks can be upsetting and even dangerous especially when they are used to inject improper inputs to mislead users. However, to date, there is no comprehensive study on the extent of improper input validation (IIV) vulnerabilities and the feasibility of their exploits in MCSs across domains. In this work, we leverage the fact that MCS interface with their participants through mobile apps to design tools and new methodologies embodied in an end-to-end feedback-driven analysis framework which we use to study 10 popular and previously unexplored services in five different domains. Using our framework we send tens of thousands of API requests with automatically generated input values to characterize their IIV attack surface. Alarmingly, we found that most of them (8/10) suffer from grave IIV vulnerabilities which allow an adversary to launch data poisoning attacks at scale: 7400 spoofed API requests were successful in faking online posts for robberies, gunshots, and other dangerous incidents, faking fitness activities with supernatural speeds and distances among many others. Lastly, we discuss easy to implement and deploy mitigation strategies which can greatly reduce the IIV attack surface and argue for their use as a necessary complementary measure working toward trustworthy mobile crowdsourcing services.

cs.CR↗

arXiv2021

Open, Sesame! Introducing Access Control to Voice Services

Personal voice assistants (VAs) are shown to be vulnerable against record-and-replay, and other acoustic attacks which allow an adversary to gain unauthorized control of connected devices within a smart home. Existing defenses either lack detection and management capabilities or are too coarse-grained to enable flexible policies on par with other computing interfaces. In this work, we present Sesame, a lightweight framework for edge devices which is the first to enable fine-grained access control of smart-home voice commands. Sesame combines three components: Automatic Speech Recognition, Natural Language Understanding (NLU) and a Policy module. We implemented Sesame on Android devices and demonstrate that our system can enforce security policies for both Alexa and Google Home in real-time (362ms end-to-end inference time), with a lightweight (<25MB) NLU model which exhibits minimal accuracy loss compared to its non-compact equivalent.

cs.CR↗

arXiv2021

Temporal Consistency Checks to Detect LiDAR Spoofing Attacks on Autonomous Vehicle Perception

LiDAR sensors are used widely in Autonomous Vehicles for better perceiving the environment which enables safer driving decisions. Recent work has demonstrated serious LiDAR spoofing attacks with alarming consequences. In particular, model-level LiDAR spoofing attacks aim to inject fake depth measurements to elicit ghost objects that are erroneously detected by 3D Object Detectors, resulting in hazardous driving decisions. In this work, we explore the use of motion as a physical invariant of genuine objects for detecting such attacks. Based on this, we propose a general methodology, 3D Temporal Consistency Check (3D-TC2), which leverages spatio-temporal information from motion prediction to verify objects detected by 3D Object Detectors. Our preliminary design and implementation of a 3D-TC2 prototype demonstrates very promising performance, providing more than 98% attack detection rate with a recall of 91% for detecting spoofed Vehicle (Car) objects, and is able to achieve real-time detection at 41Hz

cs.CR↗

arXiv2021

Layer-wise Characterization of Latent Information Leakage in Federated Learning

Training deep neural networks via federated learning allows clients to share, instead of the original data, only the model trained on their data. Prior work has demonstrated that in practice a client's private information, unrelated to the main learning task, can be discovered from the model's gradients, which compromises the promised privacy protection. However, there is still no formal approach for quantifying the leakage of private information via the shared updated model or gradients. In this work, we analyze property inference attacks and define two metrics based on (i) an adaptation of the empirical $\mathcal{V}$-information, and (ii) a sensitivity analysis using Jacobian matrices allowing us to measure changes in the gradients with respect to latent information. We show the applicability of our proposed metrics in localizing private latent information in a layer-wise manner and in two settings where (i) we have or (ii) we do not have knowledge of the attackers' capabilities. We evaluate the proposed metrics for quantifying information leakage on three real-world datasets using three benchmark models.

cs.CR↗

arXiv2021

Shadow-Catcher: Looking Into Shadows to Detect Ghost Objects in Autonomous Vehicle 3D Sensing

LiDAR-driven 3D sensing allows new generations of vehicles to achieve advanced levels of situation awareness. However, recent works have demonstrated that physical adversaries can spoof LiDAR return signals and deceive 3D object detectors to erroneously detect "ghost" objects. Existing defenses are either impractical or focus only on vehicles. Unfortunately, it is easier to spoof smaller objects such as pedestrians and cyclists, but harder to defend against and can have worse safety implications. To address this gap, we introduce Shadow-Catcher, a set of new techniques embodied in an end-to-end prototype to detect both large and small ghost object attacks on 3D detectors. We characterize a new semantically meaningful physical invariant (3D shadows) which Shadow-Catcher leverages for validating objects. Our evaluation on the KITTI dataset shows that Shadow-Catcher consistently achieves more than 94% accuracy in identifying anomalous shadows for vehicles, pedestrians, and cyclists, while it remains robust to a novel class of strong "invalidation" attacks targeting the defense system. Shadow-Catcher can achieve real-time detection, requiring only between 0.003s-0.021s on average to process an object in a 3D point cloud on commodity hardware and achieves a 2.17x speedup compared to prior work

cs.CR↗

arXiv2021

Object Removal Attacks on LiDAR-based 3D Object Detectors

LiDARs play a critical role in Autonomous Vehicles' (AVs) perception and their safe operations. Recent works have demonstrated that it is possible to spoof LiDAR return signals to elicit fake objects. In this work we demonstrate how the same physical capabilities can be used to mount a new, even more dangerous class of attacks, namely Object Removal Attacks (ORAs). ORAs aim to force 3D object detectors to fail. We leverage the default setting of LiDARs that record a single return signal per direction to perturb point clouds in the region of interest (RoI) of 3D objects. By injecting illegitimate points behind the target object, we effectively shift points away from the target objects' RoIs. Our initial results using a simple random point selection strategy show that the attack is effective in degrading the performance of commonly used 3D object detection models.

cs.CV↗

arXiv2020

Smartphone Security Behavioral Scale: A New Psychometric Measurement for Smartphone Security

Despite widespread use of smartphones, there is no measurement standard targeted at smartphone security behaviors. In this paper we translate a well-known cybersecurity behavioral scale into the smartphone domain and show that we can improve on this translation by following an established psychometrics approach surveying 1011 participants. We design a new 14-item Smartphone Security Behavioral Scale (SSBS) exhibiting high reliability and good fit to a two-component behavioural model based on technical versus social protection strategies. We then demonstrate how SSBS can be applied to measure the influence of mental health issues on smartphone security behavior intentions. We found significant correlations that predict SSBS profiles from three types of MHIs. Conversely, we are able to predict presence of MHIs using SSBS profiles.We obtain prediction AUCs of 72.1% for Internet addiction,75.8% for depression and 66.2% for insomnia.

cs.CR↗