cs.CR

arXiv:2501.06729v1 Announce Type: new Abstract: Federated Learning (FL) enables multiple users to collaboratively train a global model in a distributed manner without revealing their personal data. However, FL remains vulnerable to model poisoning attacks, where malicious actors inject crafted updates to compromise the global model's accuracy. These vulnerabilities are particularly severe in non-homogeneous environments, where clients exhibit varying proportions of class labels, resulting in heterogeneous updates. In such settings, benign outliers are often misclassified as false positives, while maliciously crafted uploads evade detection and are aggregated at the server. Existing defense mechanisms struggle in such real-world settings, resulting in significant declines in the global FL model's performance. We propose a novel defense mechanism, Kernel-based Trust Segmentation (KeTS), to counter model poisoning attacks. Unlike existing approaches, KeTS analyzes the evolution of each client's updates and effectively segments malicious clients using Kernel Density Estimation (KDE), even in the presence of benign outliers. We thoroughly evaluate KeTS's performance against the six most effective model poisoning attacks (i.e., Trim-Attack, Krum-Attack, Min-Max attack, Min-Sum attack, and their variants) on two different datasets (i.e., MNIST and Fashion-MNIST) and compare its performance with three classical robust schemes (i.e., Krum, Trim-Mean, and Median) and a state-of-the-art defense (i.e., FLTrust). Our results show that KeTS outperforms the existing defenses in every attack setting; beating the best-performing defense by an overall average of >24% (on MNIST) and >14% (on Fashion-MNIST). A series of further experiments (varying poisoning approaches, attacker population, etc.) reveal the consistent and superior performance of KeTS under diverse conditions.

arXiv:2501.06227v1 Announce Type: new Abstract: This paper reviews the state-of-the-art in deepfake generation and detection, focusing on modern deep learning technologies and tools based on the latest scientific advancements. The rise of deepfakes, leveraging techniques like Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Diffusion models and other generative models, presents significant threats to privacy, security, and democracy. This fake media can deceive individuals, discredit real people and organizations, facilitate blackmail, and even threaten the integrity of legal, political, and social systems. Therefore, finding appropriate solutions to counter the potential threats posed by this technology is essential. We explore various deepfake methods, including face swapping, voice conversion, reenactment and lip synchronization, highlighting their applications in both benign and malicious contexts. The review critically examines the ongoing "arms race" between deepfake generation and detection, analyzing the challenges in identifying manipulated contents. By examining current methods and highlighting future research directions, this paper contributes to a crucial understanding of this rapidly evolving field and the urgent need for robust detection strategies to counter the misuse of this powerful technology. While focusing primarily on audio, image, and video domains, this study allows the reader to easily grasp the latest advancements in deepfake generation and detection.

arXiv:2501.06650v1 Announce Type: new Abstract: Split Learning (SL) is a distributed deep learning approach enabling multiple clients and a server to collaboratively train and infer on a shared deep neural network (DNN) without requiring clients to share their private local data. The DNN is partitioned in SL, with most layers residing on the server and a few initial layers and inputs on the client side. This configuration allows resource-constrained clients to participate in training and inference. However, the distributed architecture exposes SL to backdoor attacks, where malicious clients can manipulate local datasets to alter the DNN's behavior. Existing defenses from other distributed frameworks like Federated Learning are not applicable, and there is a lack of effective backdoor defenses specifically designed for SL. We present SafeSplit, the first defense against client-side backdoor attacks in Split Learning (SL). SafeSplit enables the server to detect and filter out malicious client behavior by employing circular backward analysis after a client's training is completed, iteratively reverting to a trained checkpoint where the model under examination is found to be benign. It uses a two-fold analysis to identify client-induced changes and detect poisoned models. First, a static analysis in the frequency domain measures the differences in the layer's parameters at the server. Second, a dynamic analysis introduces a novel rotational distance metric that assesses the orientation shifts of the server's layer parameters during training. Our comprehensive evaluation across various data distributions, client counts, and attack scenarios demonstrates the high efficacy of this dual analysis in mitigating backdoor attacks while preserving model utility.

arXiv:2501.06686v1 Announce Type: new Abstract: Neural ordinary differential equations (NODEs) are an emerging paradigm in scientific computing for modeling dynamical systems. By accurately learning underlying dynamics in data in the form of differential equations, NODEs have been widely adopted in various domains, such as healthcare, finance, computer vision, and language modeling. However, there remains a limited understanding of the privacy implications of these fundamentally different models, particularly with regard to their membership inference risks. In this work, we study the membership inference risks associated with NODEs. We first comprehensively evaluate NODEs against membership inference attacks. We show that NODEs are twice as resistant to these privacy attacks compared to conventional feedforward models such as ResNets. By analyzing the variance in membership risks across different NODE models, we identify the factors that contribute to their lower risks. We then demonstrate, both theoretically and empirically, that membership inference risks can be further mitigated by utilizing a stochastic variant of NODEs: Neural stochastic differential equations (NSDEs). We show that NSDEs are differentially-private (DP) learners that provide the same provable privacy guarantees as DP-SGD, the de-facto mechanism for training private models. NSDEs are also effective in mitigating existing membership inference attacks, demonstrating risks comparable to private models trained with DP-SGD while offering an improved privacy-utility trade-off. Moreover, we propose a drop-in-replacement strategy that efficiently integrates NSDEs into conventional feedforward models to enhance their privacy.

arXiv:2501.06239v1 Announce Type: new Abstract: Cyber Threat Intelligence (CTI) is critical for mitigating threats to organizations, governments, and institutions, yet the necessary data are often dispersed across diverse formats. AI-driven solutions for CTI Information Extraction (IE) typically depend on high-quality, annotated data, which are not always available. This paper introduces 0-CTI, a scalable AI-based framework designed for efficient CTI Information Extraction. Leveraging advanced Natural Language Processing (NLP) techniques, particularly Transformer-based architectures, the proposed system processes complete text sequences of CTI reports to extract a cyber ontology of named entities and their relationships. Our contribution is the development of 0-CTI, the first modular framework for CTI Information Extraction that supports both supervised and zero-shot learning. Unlike existing state-of-the-art models that rely heavily on annotated datasets, our system enables fully dataless operation through zero-shot methods for both Entity and Relation Extraction, making it adaptable to various data availability scenarios. Additionally, our supervised Entity Extractor surpasses current state-of-the-art performance in cyber Entity Extraction, highlighting the dual strength of the framework in both low-resource and data-rich environments. By aligning the system's outputs with the Structured Threat Information Expression (STIX) format, a standard for information exchange in the cybersecurity domain, 0-CTI standardizes extracted knowledge, enhancing communication and collaboration in cybersecurity operations.

arXiv:2501.06264v1 Announce Type: new Abstract: This research introduces a robust detection system against malicious network traffic, leveraging hierarchical structures and self-attention mechanisms. The proposed system includes a Packet Segmenter that divides a given raw network packet into fixed-size segments that are fed to the HPAC-IDS. The experiments performed on CIC-IDS2017 dataset show that the system exhibits high accuracy and low false positive rates while demonstrating resilience against diverse adversarial methods like Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), and Wasserstein GAN (WGAN). The model's ability to withstand adversarial perturbations is attributed to the fusion of hierarchical attention mechanisms and convolutional neural networks, resulting in a 0% to 10% adversarial attack severity under tested adversarial attacks with different segment sizes, surpassing the state-of-the-art model in detection performance and adversarial attack robustness.

arXiv:2501.06234v1 Announce Type: new Abstract: We present LionsOS, an operating system for security- and safety-critical embedded systems. LionsOS is based on the formally verified seL4 microkernel and designed with verification in mind. It uses a static architecture and features a highly modular design driven by strict separation of concerns and a focus on simplicity. We demonstrate that LionsOS outperforms Linux.

arXiv:2501.06646v1 Announce Type: new Abstract: With lowering thresholds, transparently defending against Rowhammer within DRAM is challenging due to the lack of time to perform mitigation. Commercially deployed in-DRAM defenses like TRR that steal time from normal refreshes~(REF) to perform mitigation have been proven ineffective against Rowhammer. In response, a new Refresh Management (RFM) interface has been added to the DDR5 specifications. RFM provides dedicated time to an in-DRAM defense to perform mitigation. Several recent works have used RFM for the intended purpose - building better Rowhammer defenses. However, to the best of our knowledge, no prior study has looked at the potential security implications of this new feature if an attacker subjects it to intentional misuse. Our paper shows that RFM introduces new side effects in the system - the activity of one bank causes interference with the operation of the other banks. Thus, the latency of a bank becomes dependent on the activity of other banks. We use these side effects to build two new attacks. First, a novel memory-based covert channel, which has a bandwidth of up to 31.3 KB/s, and is also effective even in a bank-partitioned system. Second, a new Denial-of-Service (DOS) attack pattern that exploits the activity within a single bank to reduce the performance of the other banks. Our experiments on SPEC2017, PARSEC, and LIGRA workloads show a slowdown of up to 67\% when running alongside our DOS pattern. We also discuss potential countermeasures for our attacks.

arXiv:2501.06237v1 Announce Type: new Abstract: In the evolving landscape of data privacy, the anonymization of electric load profiles has become a critical issue, especially with the enforcement of the General Data Protection Regulation (GDPR) in Europe. These electric load profiles, which are essential datasets in the energy industry, are classified as personal behavioral data, necessitating stringent protective measures. This article explores the implications of this classification, the importance of data anonymization, and the potential of forecasting using microaggregated data. The findings underscore that effective anonymization techniques, such as microaggregation, do not compromise the performance of forecasting models under certain conditions (i.e., forecasting aggregated). In such an aggregated level, microaggregated data maintains high levels of utility, with minimal impact on forecasting accuracy. The implications for the energy sector are profound, suggesting that privacy-preserving data practices can be integrated into smart metering technology applications without hindering their effectiveness.

arXiv:2501.06367v1 Announce Type: new Abstract: Physical Unclonable Functions (PUFs) based on Non-Volatile Memory (NVM) technology have emerged as a promising solution for secure authentication and cryptographic applications. By leveraging the multi-level cell (MLC) characteristic of NVMs, these PUFs can generate a wide range of unique responses, enhancing their resilience to machine learning (ML) modeling attacks. However, a significant issue with NVM-based PUFs is their endurance problem; frequent write operations lead to wear and degradation over time, reducing the reliability and lifespan of the PUF. This paper addresses these issues by offering a comprehensive model to predict and analyze the effects of endurance changes on NVM PUFs. This model provides insights into how wear impacts the PUF's quality and helps in designing more robust PUFs. Building on this model, we present a novel design for NVM PUFs that significantly improves endurance. Our design approach incorporates advanced techniques to distribute write operations more evenly and reduce stress on individual cells. The result is an NVM PUF that demonstrates a $62\times$ improvement in endurance compared to current state-of-the-art solutions while maintaining protection against learning-based attacks.

arXiv:2501.06399v1 Announce Type: new Abstract: From a simple text prompt, generative-AI image models can create stunningly realistic and creative images bounded, it seems, by only our imagination. These models have achieved this remarkable feat thanks, in part, to the ingestion of billions of images collected from nearly every corner of the internet. Many creators have understandably expressed concern over how their intellectual property has been ingested without their permission or a mechanism to opt out of training. As a result, questions of fair use and copyright infringement have quickly emerged. We describe a method that allows us to determine if a model was trained on a specific image or set of images. This method is computationally efficient and assumes no explicit knowledge of the model architecture or weights (so-called black-box membership inference). We anticipate that this method will be crucial for auditing existing models and, looking ahead, ensuring the fairer development and deployment of generative AI models.

arXiv:2501.06504v1 Announce Type: new Abstract: Biometric authentication is increasingly popular for its convenience and accuracy. However, while recent advancements focus on reducing errors and expanding modalities, the reliability of reported performance metrics often remains overlooked. Understanding reliability is critical, as it communicates how accurately reported error rates represent a system's actual performance, considering the uncertainty in error-rate estimates from test data. Currently, there is no widely accepted standard for reporting these uncertainties and indeed biometric studies rarely provide reliability estimates, limiting comparability and interpretation. To address this gap, we introduce BioQuake--a measure to estimate uncertainty in biometric verification systems--and empirically validate it on four systems and three datasets. Based on BioQuake, we provide simple guidelines for estimating performance uncertainty and facilitating reliable reporting. Additionally, we apply BioQuake to analyze biometric recognition performance on 62 biometric datasets used in research across eight modalities: face, fingerprint, gait, iris, keystroke, eye movement, Electroencephalogram (EEG), and Electrocardiogram (ECG). Our analysis shows that reported state-of-the-art performance often deviates significantly from actual error rates, potentially leading to inaccurate conclusions. To support researchers and foster the development of more reliable biometric systems and datasets, we release BioQuake as an easy-to-use web tool for reliability calculations.

arXiv:2501.06515v1 Announce Type: new Abstract: This paper proposes a three-step Secret Santa algorithm with setup that leverages Zero Knowledge Proofs (ZKP) to set up gift sender/receiver relations while maintaining the sender's confidentiality. The algorithm maintains a permutational derangement and does not require a central authority to perform successfully. The described approach can be implemented in Solidity provided the integration with a transaction relayer.

arXiv:2501.06531v1 Announce Type: new Abstract: Recent advances have improved the throughput and latency of blockchains by processing transactions accessing different parts of the state concurrently. However, these systems are unable to concurrently process (a) transactions accessing the same state, even if they are (almost) commutative, e.g., payments much smaller than an account's balance, and (b) multi-party transactions, e.g., asset swaps. Moreover, they are slow to recover from contention, requiring once-in-a-day synchronization. We present Stingray, a novel blockchain architecture that addresses these limitations. The key conceptual contributions are a replicated bounded counter that processes (almost) commutative transactions concurrently, and a FastUnlock protocol that uses a fallback consensus protocol for fast contention recovery. We prove Stingray's security in an asynchronous network with Byzantine faults and demonstrate on a global testbed that Stingray achieves 10,000 times the throughput of prior systems for commutative workloads.

arXiv:2501.06533v1 Announce Type: new Abstract: The widespread adoption of facial recognition (FR) models raises serious concerns about their potential misuse, motivating the development of anti-facial recognition (AFR) to protect user facial privacy. In this paper, we argue that the static FR strategy, predominantly adopted in prior literature for evaluating AFR efficacy, cannot faithfully characterize the actual capabilities of determined trackers who aim to track a specific target identity. In particular, we introduce \emph{\ourAttack}, a dynamic FR strategy where the model's gallery database is iteratively updated with newly recognized target identity images. Surprisingly, such a simple approach renders all the existing AFR protections ineffective. To mitigate the privacy threats posed by DynTracker, we advocate for explicitly promoting diversity in the AFR-protected images. We hypothesize that the lack of diversity is the primary cause of the failure of existing AFR methods. Specifically, we develop \emph{DivTrackee}, a novel method for crafting diverse AFR protections that builds upon a text-guided image generation framework and diversity-promoting adversarial losses. Through comprehensive experiments on various facial image benchmarks and feature extractors, we demonstrate DynTracker's strength in breaking existing AFR methods and the superiority of DivTrackee in preventing user facial images from being identified by dynamic FR strategies. We believe our work can act as an important initial step towards developing more effective AFR methods for protecting user facial privacy against determined trackers.

arXiv:2501.06267v1 Announce Type: new Abstract: We describe a protocol for creating, updating, and revoking digital diplomas that we anticipate would make use of the protocol for transferring digital assets elaborated by Goodell, Toliver, and Nakib. Digital diplomas would maintain their own state, and make use a distributed ledger as a mechanism for verifying their integrity. The use of a distributed ledger enables verification of the state of an asset without the need to contact the issuing institution, and we describe how the integrity of a diploma issued in this way can persist even in the absence of the issuing institution.

arXiv:2501.06281v1 Announce Type: new Abstract: Zero Trust Architectures (ZTA) fundamentally redefine network security by adopting a "trust nothing, verify everything" approach that requires identity verification for all access. Conventional discrete access control measures have proven inadequate since they do not consider evolving user activities and contextual threats, leading to internal threats and enhanced attacks. This research applies the proposed AI-driven, autonomous, identity-based threat segmentation in ZTA, along with real-time identity analytics for fine-grained, real-time mechanisms. Some of the sharp practices include using the behavioral analytics approach to provide real-time risk scores, such as analyzing the patterns used for logging into the system, the access sought, and the resources used. Permissions are adjusted using machine learning models that take into account context-aware factors like geolocation, device type, and access time. Automated threat segmentation helps analysts identify multiple compromised identities in real-time, thus minimizing the likelihood of a breach advancing. The system's use cases are based on real scenarios; for example, insider threats in global offices demonstrate how compromised accounts are detected and locked. This work outlines measures to address privacy issues, false positives, and scalability concerns. This research enhances the security of other critical areas of computer systems by providing dynamic access governance, minimizing insider threats, and supporting dynamic policy enforcement while ensuring that the needed balance between security and user productivity remains a top priority. We prove via comparative analyses that the model is precise and scalable.

arXiv:2501.06620v1 Announce Type: new Abstract: The cumulative distribution function (CDF) is fundamental due to its ability to reveal information about random variables, making it essential in studies that require privacy-preserving methods to protect sensitive data. This paper introduces a novel privacy-preserving CDF method inspired by the functional analysis and functional mechanism. Our approach projects the empirical CDF into a predefined space, approximating it using specific functions, and protects the coefficients to achieve a differentially private empirical CDF. Compared to existing methods like histogram queries and adaptive quantiles, our method is preferable in decentralized settings and scenarios where CDFs must be updated with newly collected data.

arXiv:2501.06305v1 Announce Type: new Abstract: Cloud computing has emerged as a crucial solution for managing data- and compute-intensive workflows, offering scalability to address dynamic demands. However, security concerns persist, especially for workflows involving sensitive data and tasks. One of the main gaps in the literature is the lack of robust and flexible measures for reacting to these security violations. To address this, we propose an innovative approach leveraging Reinforcement Learning (RL) to formulate adaptation chains, responding effectively to security violations within cloud-based workflows. These chains consist of sequences of adaptation actions tailored to attack characteristics, workflow dependencies, and user-defined requirements. Unlike conventional single-task adaptations, adaptation chains provide a comprehensive mitigation strategy by taking into account both control and data dependencies between tasks, thereby accommodating conflicting objectives effectively. Moreover, our RL-based approach uses insights from past responses to mitigate uncertainties associated with adaptation costs. We evaluate the method using our jBPM and Cloudsim Plus based implementation and compare the impact of selected adaptation chains on workflows with the single adaptation approach. Results demonstrate that the adaptation chain approach outperforms in terms of total adaptation cost, offering resilience and adaptability against security threats.

arXiv:2501.06798v1 Announce Type: new Abstract: This study reveals the vulnerabilities of Wireless Local Area Networks (WLAN) sensing, under the scope of joint communication and sensing (JCAS), focusing on target spoofing and deceptive jamming techniques. We use orthogonal frequency-division multiplexing (OFDM) to explore how adversaries can exploit WLAN's sensing capabilities to inject false targets and disrupt normal operations. Unlike traditional methods that require sophisticated digital radio-frequency memory hardware, we demonstrate that much simpler software-defined radios can effectively serve as deceptive jammers in WLAN settings. Through comprehensive modeling and practical experiments, we show how deceptive jammers can manipulate the range-Doppler map (RDM) by altering signal integrity, thereby posing significant security threats to OFDM-based JCAS systems. Our findings comprehensively evaluate jammer impact on RDMs and propose several jamming strategies that vary in complexity and detectability.