arXiv subjects

Michail Maniatakos

Publications and source records attributed to Michail Maniatakos.

At least 19 recordsLinked to original sources

arXiv2026

SEEK: Secure and Efficient Encrypted Keyword Search For Privacy-Preserving Messaging Protocols

Encrypted communication protects sensitive user data but can facilitate harmful or unlawful exchanges, creating a trade-off between detecting dangerous messages and preserving end-user privacy. To address this, we propose SEEK, a practical and efficient encrypted keyword-search protocol for privacy-preserving messaging that combines homomorphic encryption with secure two-party computation (2PC). SEEK first partitions messages into ciphertext fragments with the minimum sufficient overlap, then homomorphically correlates them using encrypted keyword trapdoors. For long messages, this design can reduce sender-side encryption and upload overhead by up to two orders of magnitude over state-of-the-art baselines. It supports ASCII case-insensitive matching with one fixed-size encrypted trapdoor and one homomorphic multiplication per fragment, yielding up to 5.47x faster correlation computation than the strongest fragmentation-based baselines. SEEK then invokes 2PC-based selected decoding, blinded zero testing, and secure aggregation, revealing only the keyword presence-or-absence bit while hiding the keyword, its length, message contents, match counts, and locations. SEEK achieves 100% accuracy under case variations that result in exact-matching failures, without requiring additional trapdoors or online communication. We further realize SEEK as an end-to-end web and cross-platform mobile application. Prototype evaluation on a weekly messaging history yields an online computation time of 1.92 s per search, demonstrating the practical feasibility and efficiency of SEEK.

cs.CR↗

arXiv2026

PAPER: Privacy-Preserving Convolutional Neural Networks using Low-Degree Polynomial Approximations and Structural Optimizations on Leveled FHE

Recent work using Fully Homomorphic Encryption (FHE) has made non-interactive privacy-preserving inference of deep Convolutional Neural Networks (CNNs) possible. However, the performance of these methods remains limited by their heavy reliance on bootstrapping, a costly FHE operation applied across multiple layers that severely slows inference. Moreover, they depend on high-degree polynomial approximations of non-linear activations, which increase multiplicative depth and reduce accuracy by 2-5% compared with plaintext ReLU models. In this work, we close the accuracy gap between FHE-based non-interactive CNNs and their plaintext counterparts while achieving faster inference than existing methods. We propose a quadratic polynomial approximation of ReLU that achieves the theoretical minimum multiplicative depth for non-linear activations, together with a penalty-based training strategy. We further introduce structural optimizations that reduce the required FHE levels in CNNs by a factor of five compared with prior work, allowing us to run deep CNN models under leveled FHE without bootstrapping. To further accelerate inference and recover accuracy typically lost with polynomial approximations, we introduce parameter clustering together with a joint strategy involving data layout and ensemble techniques. Experiments with VGG and ResNet models on CIFAR and Tiny-ImageNet datasets show that our approach achieves up to 4x faster private inference than prior work, with accuracy comparable to plaintext ReLU models.

cs.CR↗

arXiv2026

Security Analysis for SCONE Logic Locking

SCONE [DAC'25] expands a logic locking interface with additional encoded inputs derived from the original primary inputs, and admits two realizations: a \textit{with-ES} variant, where the critical encoding stage is implemented in hardware, and a \textit{without-ES} variant, where the locked design directly exposes an encoded interface of width $n+m$. We show that both realizations are vulnerable, but for different reasons. For the without-ES variant, we prove that, when the added encoded inputs are deterministic linear functions of the original inputs, the valid encoded-input space remains $n$-dimensional despite the nominal expansion to $n+m$ inputs. Hence, the widened interface does not yield $m$ additional or independent brute-force dimensions. For the with-ES variant, we present a polynomial-time white-box attack that exactly recovers the added-input count and the implemented linear encoding relation from the locked netlist, achieving 100\% recovery over all evaluated instances. We also develop a black-box procedure that certifies the same dimensionality collapse from valid encoded-input samples without reconstructing the hidden encoder. Experiments on ISCAS-85 and ITC-99 benchmarks validate both results, and we further demonstrate exact white-box recovery on an ARM Cortex-M0 RTL benchmark. Finally, we propose a lightweight non-linear mitigation and show that it does not exhibit the vulnerabilities identified in this paper under all representative attack sets considered in SCONE.

cs.CR↗

arXiv2026

CHEHAB RL: Learning to Optimize Fully Homomorphic Encryption Computations

Fully Homomorphic Encryption (FHE) enables computations directly on encrypted data, but its high computational cost remains a significant barrier. Writing efficient FHE code is a complex task requiring cryptographic expertise, and finding the optimal sequence of program transformations is often intractable. In this paper, we propose CHEHAB RL, a novel framework that leverages deep reinforcement learning (RL) to automate FHE code optimization. Instead of relying on predefined heuristics or combinatorial search, our method trains an RL agent to learn an effective policy for applying a sequence of rewriting rules to automatically vectorize scalar FHE code while reducing instruction latency and noise growth. The proposed approach supports the optimization of both structured and unstructured code. To train the agent, we synthesize a diverse dataset of computations using a large language model (LLM). We integrate our proposed approach into the CHEHAB FHE compiler and evaluate it on a suite of benchmarks, comparing its performance against Coyote, a state-of-the-art vectorizing FHE compiler. The results show that our approach generates code that is $5.3\times$ faster in execution, accumulates $2.54\times$ less noise, while the compilation process itself is $27.9\times$ faster than Coyote (geometric means).

cs.CR↗

arXiv2026

@NTT: Algorithm-Targeted NTT hardware acceleration via Design-Time Constant Optimization

The Number Theoretic Transform (NTT) is a critical computational bottleneck in many lattice-based postquantum cryptographic (PQC) algorithms. By leveraging the Fast Fourier Transform (FFT) algorithm, the NTT of a polynomial of degree N - 1 can be computed with a time complexity of O(N log N). Hardware implementation of NTT is generally preferred over software ones, as the latter are significantly slower due to complex memory access patterns and modular arithmetic operations. Achieving maximum throughput in hardware, however, typically demands a prohibitively large number of butterfly unit instantiations. In this work, we propose @NTT, which exploits the fact that the ring parameters in these algorithms are fixed, enabling design-time constant optimization and achieving the maximum throughput of N-point NTT per clock cycle with a compact hardware footprint. Our case study on the Dilithium NTT, implemented using the TSMC 28 nm library, operates at a clock frequency of 1.0 GHz with an area of 1.45 mm^2. On FPGA, the design achieves a throughput-per-LUT that is 5.2x higher than the state-of-the-art implementation.

cs.CR↗

arXiv2025

Fully Decentralized Certified Unlearning

Machine unlearning (MU) seeks to remove the influence of specified data from a trained model in response to privacy requests or data poisoning. While certified unlearning has been analyzed in centralized and server-orchestrated federated settings (via guarantees analogous to differential privacy, DP), the decentralized setting -- where peers communicate without a coordinator remains underexplored. We study certified unlearning in decentralized networks with fixed topologies and propose RR-DU, a random-walk procedure that performs one projected gradient ascent step on the forget set at the unlearning client and a geometrically distributed number of projected descent steps on the retained data elsewhere, combined with subsampled Gaussian noise and projection onto a trust region around the original model. We provide (i) convergence guarantees in the convex case and stationarity guarantees in the nonconvex case, (ii) $(\varepsilon,δ)$ network-unlearning certificates on client views via subsampled Gaussian Rényi DP (RDP) with segment-level subsampling, and (iii) deletion-capacity bounds that scale with the forget-to-local data ratio and quantify the effect of decentralization (network mixing and randomized subsampling) on the privacy-utility trade-off. Empirically, on image benchmarks (MNIST, CIFAR-10), RR-DU matches a given $(\varepsilon,δ)$ while achieving higher test accuracy than decentralized DP baselines and reducing forget accuracy to random guessing ($\approx 10\%$).

cs.LG↗

arXiv2025

BlendFL: Blended Federated Learning for Handling Multimodal Data Heterogeneity

One of the key challenges of collaborative machine learning, without data sharing, is multimodal data heterogeneity in real-world settings. While Federated Learning (FL) enables model training across multiple clients, existing frameworks, such as horizontal and vertical FL, are only effective in `ideal' settings that meet specific assumptions. Hence, they struggle to address scenarios where neither all modalities nor all samples are represented across the participating clients. To address this gap, we propose BlendFL, a novel FL framework that seamlessly blends the principles of horizontal and vertical FL in a synchronized and non-restrictive fashion despite the asymmetry across clients. Specifically, any client within BlendFL can benefit from either of the approaches, or both simultaneously, according to its available dataset. In addition, BlendFL features a decentralized inference mechanism, empowering clients to run collaboratively trained local models using available local data, thereby reducing latency and reliance on central servers for inference. We also introduce BlendAvg, an adaptive global model aggregation strategy that prioritizes collaborative model updates based on each client's performance. We trained and evaluated BlendFL and other state-of-the-art baselines on three classification tasks using a large-scale real-world multimodal medical dataset and a popular multimodal benchmark. Our results highlight BlendFL's superior performance for both multimodal and unimodal classification. Ablation studies demonstrate BlendFL's faster convergence compared to traditional approaches, accelerating collaborative learning. Overall, in our study we highlight the potential of BlendFL for handling multimodal data heterogeneity for collaborative learning in real-world settings where data privacy is crucial, such as in healthcare and finance.

cs.LG↗

arXiv2025

DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systems

Federated Unlearning (FU) enables clients to remove the influence of specific data from a collaboratively trained shared global model, addressing regulatory requirements such as GDPR and CCPA. However, this unlearning process introduces a new privacy risk: A malicious server may exploit unlearning updates to reconstruct the data requested for removal, a form of Data Reconstruction Attack (DRA). While DRAs for machine unlearning have been studied extensively in centralized Machine Learning-as-a-Service (MLaaS) settings, their applicability to FU remains unclear due to the decentralized, client-driven nature of FU. This work presents DRAUN, the first attack framework to reconstruct unlearned data in FU systems. DRAUN targets optimization-based unlearning methods, which are widely adopted for their efficiency. We theoretically demonstrate why existing DRAs targeting machine unlearning in MLaaS fail in FU and show how DRAUN overcomes these limitations. We validate our approach through extensive experiments on four datasets and four model architectures, evaluating its performance against five popular unlearning methods, effectively demonstrating that state-of-the-art FU methods remain vulnerable to DRAs.

cs.LG↗

arXiv2025

LLMPot: Dynamically Configured LLM-based Honeypot for Industrial Protocol and Physical Process Emulation

Industrial Control Systems (ICS) are extensively used in critical infrastructures ensuring efficient, reliable, and continuous operations. However, their increasing connectivity and addition of advanced features make them vulnerable to cyber threats, potentially leading to severe disruptions in essential services. In this context, honeypots play a vital role by acting as decoy targets within ICS networks, or on the Internet, helping to detect, log, analyze, and develop mitigations for ICS-specific cyber threats. Deploying ICS honeypots, however, is challenging due to the necessity of accurately replicating industrial protocols and device characteristics, a crucial requirement for effectively mimicking the unique operational behavior of different industrial systems. Moreover, this challenge is compounded by the significant manual effort required in also mimicking the control logic the PLC would execute, in order to capture attacker traffic aiming to disrupt critical infrastructure operations. In this paper, we propose LLMPot, a novel approach for designing honeypots in ICS networks harnessing the potency of Large Language Models (LLMs). LLMPot aims to automate and optimize the creation of realistic honeypots with vendor-agnostic configurations, and for any control logic, aiming to eliminate the manual effort and specialized knowledge traditionally required in this domain. We conducted extensive experiments focusing on a wide array of parameters, demonstrating that our LLM-based approach can effectively create honeypot devices implementing different industrial protocols and diverse control logic.

cs.CR↗

arXiv2025

Veritas: Deterministic Verilog Code Synthesis from LLM-Generated Conjunctive Normal Form

Automated Verilog code synthesis poses significant challenges and typically demands expert oversight. Traditional high-level synthesis (HLS) methods often fail to scale for real-world designs. While large language models (LLMs) have enhanced scalability, they often introduce syntactical and logical errors requiring extensive post-generation verification. Here, we introduce a novel conjunctive normal form (CNF)-guided synthesis methodology. The idea is to have an LLM generate CNF clauses, a format widely used for formal verification and synthesis validation in hardware design, but here it is used to formally describe the desired circuit functionality. These CNF specifications are then deterministically converted into Verilog, ensuring correctness by construction. Our approach fine-tunes an open-source and lightweight LLM, namely the CPU-deployable LLama-3.2-3B-Instruct model (parameters < 4B), on a dataset of standard RTL components. Experimental results demonstrate that our approach reliably produces functionally correct Verilog code on the first attempt, compared to other lightweight open-source SoTA works such as Verigen (2B parameters) and RTLCoder (4-bit quantized with around 7B parameters). We will release our method and data in full post peer-review.

cs.AR↗

arXiv2025

HowkGPT: Investigating the Detection of ChatGPT-generated University Student Homework through Context-Aware Perplexity Analysis

As the use of Large Language Models (LLMs) in text generation tasks proliferates, concerns arise over their potential to compromise academic integrity. The education sector currently tussles with distinguishing student-authored homework assignments from AI-generated ones. This paper addresses the challenge by introducing HowkGPT, designed to identify homework assignments generated by AI. HowkGPT is built upon a dataset of academic assignments and accompanying metadata [17] and employs a pretrained LLM to compute perplexity scores for student-authored and ChatGPT-generated responses. These scores then assist in establishing a threshold for discerning the origin of a submitted assignment. Given the specificity and contextual nature of academic work, HowkGPT further refines its analysis by defining category-specific thresholds derived from the metadata, enhancing the precision of the detection. This study emphasizes the critical need for effective strategies to uphold academic integrity amidst the growing influence of LLMs and provides an approach to ensuring fair and accurate grading in educational institutions.

cs.CL↗

arXiv2025

ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning

Backdoor attacks embed hidden functionalities in deep neural networks (DNN), triggering malicious behavior with specific inputs. Advanced defenses monitor anomalous DNN inferences to detect such attacks. However, concealed backdoors evade detection by maintaining a low pre-deployment attack success rate (ASR) and restoring high ASR post-deployment via machine unlearning. Existing concealed backdoors are often constrained by requiring white-box or black-box access or auxiliary data, limiting their practicality when such access or data is unavailable. This paper introduces ReVeil, a concealed backdoor attack targeting the data collection phase of the DNN training pipeline, requiring no model access or auxiliary data. ReVeil maintains low pre-deployment ASR across four datasets and four trigger patterns, successfully evades three popular backdoor detection methods, and restores high ASR post-deployment through machine unlearning.

cs.CR↗

arXiv2024

RTL-Breaker: Assessing the Security of LLMs against Backdoor Attacks on HDL Code Generation

Large language models (LLMs) have demonstrated remarkable potential with code generation/completion tasks for hardware design. In fact, LLM-based hardware description language (HDL) code generation has enabled the industry to realize complex designs more quickly, reducing the time and effort required in the development cycle. However, the increased reliance on such automation introduces critical security risks. Notably, given that LLMs have to be trained on vast datasets of codes that are typically sourced from publicly available repositories (often without thorough validation), LLMs are susceptible to so-called data poisoning or backdoor attacks. Here, attackers inject malicious code for the training data, which can be carried over into the HDL code generated by LLMs. This threat vector can compromise the security and integrity of entire hardware systems. In this work, we propose RTL-Breaker, a novel backdoor attack framework on LLM-based HDL code generation. RTL-Breaker provides an in-depth analysis for essential aspects of this novel problem: 1) various trigger mechanisms versus their effectiveness for inserting malicious modifications, and 2) side-effects by backdoor attacks on code generation in general, i.e., impact on code quality. RTL-Breaker emphasizes the urgent need for more robust measures to safeguard against such attacks. Toward that end, we open-source our framework and all data.

cs.CR↗

arXiv2024

CoFHEE: A Co-processor for Fully Homomorphic Encryption Execution (Extended Version)

The migration of computation to the cloud has raised concerns regarding the security and privacy of sensitive data, as their need to be decrypted before processing, renders them susceptible to potential breaches. Fully Homomorphic Encryption (FHE) serves as a countermeasure to this issue by enabling computation to be executed directly on encrypted data. Nevertheless, the execution of FHE is orders of magnitude slower compared to unencrypted computation, thereby impeding its practicality and adoption. Therefore, enhancing the performance of FHE is crucial for its implementation in real-world scenarios. In this study, we elaborate on our endeavors to design, implement, fabricate, and post-silicon validate CoFHEE, a co-processor for low-level polynomial operations targeting Fully Homomorphic Encryption execution. With a compact design area of $12mm^2$, CoFHEE features ASIC implementations of fundamental polynomial operations, including polynomial addition and subtraction, Hadamard product, and Number Theoretic Transform, which underlie most higher-level FHE primitives. CoFHEE is capable of natively supporting polynomial degrees of up to $n = 2^{14}$ with a coefficient size of 128 bits, and has been fabricated and silicon-verified using 55nm CMOS technology. To evaluate it, we conduct performance and power experiments on our chip, and compare it to state-of-the-art software implementations and other ASIC designs.

cs.CR↗

arXiv2023

FieldFuzz: In Situ Blackbox Fuzzing of Proprietary Industrial Automation Runtimes via the Network

Networked Programmable Logic Controllers (PLCs) are proprietary industrial devices utilized in critical infrastructure that execute control logic applications in complex proprietary runtime environments that provide standardized access to the hardware resources in the PLC. These control applications are programmed in domain-specific IEC 61131-3 languages, compiled into a proprietary binary format, and process data provided via industrial protocols. Control applications present an attack surface threatened by manipulated traffic. For example, remote code injection in a control application would directly allow to take over the PLC, threatening physical process damage and the safety of human operators. However, assessing the security of control applications is challenging due to domain-specific challenges and the limited availability of suitable methods. Network-based fuzzing is often the only way to test such devices but is inefficient without guidance from execution tracing. This work presents the FieldFuzz framework that analyzes the security risks posed by the Codesys runtime (used by over 400 devices from 80 industrial PLC vendors). FieldFuzz leverages efficient network-based fuzzing based on three main contributions: i) reverse-engineering enabled remote control of control applications and runtime components, ii) automated command discovery and status code extraction via network traffic and iii) a monitoring setup to allow on-system tracing and coverage computation. We use FieldFuzz to run fuzzing campaigns, which uncover multiple vulnerabilities, leading to three reported CVE IDs. To study the cross-platform applicability of FieldFuzz, we reproduce the findings on a diverse set of Industrial Control System (ICS) devices, showing a significant improvement over the state-of-the-art.

cs.CR↗

arXiv2023

Perception, performance, and detectability of conversational artificial intelligence across 32 university courses

The emergence of large language models has led to the development of powerful tools such as ChatGPT that can produce text indistinguishable from human-generated work. With the increasing accessibility of such technology, students across the globe may utilize it to help with their school work -- a possibility that has sparked discussions on the integrity of student evaluations in the age of artificial intelligence (AI). To date, it is unclear how such tools perform compared to students on university-level courses. Further, students' perspectives regarding the use of such tools, and educators' perspectives on treating their use as plagiarism, remain unknown. Here, we compare the performance of ChatGPT against students on 32 university-level courses. We also assess the degree to which its use can be detected by two classifiers designed specifically for this purpose. Additionally, we conduct a survey across five countries, as well as a more in-depth survey at the authors' institution, to discern students' and educators' perceptions of ChatGPT's use. We find that ChatGPT's performance is comparable, if not superior, to that of students in many courses. Moreover, current AI-text classifiers cannot reliably detect ChatGPT's use in school work, due to their propensity to classify human-written answers as AI-generated, as well as the ease with which AI-generated text can be edited to evade detection. Finally, we find an emerging consensus among students to use the tool, and among educators to treat this as plagiarism. Our findings offer insights that could guide policy discussions addressing the integration of AI into educational frameworks.

cs.CY↗

arXiv2023

ICSML: Industrial Control Systems ML Framework for native inference using IEC 61131-3 code

Industrial Control Systems (ICS) have played a catalytic role in enabling the 4th Industrial Revolution. ICS devices like Programmable Logic Controllers (PLCs), automate, monitor, and control critical processes in industrial, energy, and commercial environments. The convergence of traditional Operational Technology (OT) with Information Technology (IT) has opened a new and unique threat landscape. This has inspired defense research that focuses heavily on Machine Learning (ML) based anomaly detection methods that run on external IT hardware, which means an increase in costs and the further expansion of the threat landscape. To remove this requirement, we introduce the ICS machine learning inference framework (ICSML) which enables executing ML model inference natively on the PLC. ICSML is implemented in IEC 61131-3 code and provides several optimizations to bypass the limitations imposed by the domain-specific languages. Therefore, it works on every PLC without the need for vendor support. ICSML provides a complete set of components for creating full ML models similarly to established ML frameworks. We run a series of benchmarks studying memory and performance, and compare our solution to the TFLite inference framework. At the same time, we develop domain-specific model optimizations to improve the efficiency of ICSML. To demonstrate the abilities of ICSML, we evaluate a case study of a real defense for process-aware attacks targeting a desalination plant.

cs.LG↗

arXiv2023

Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learning

Federated Learning (FL) enables collaborative deep learning training across multiple participants without exposing sensitive personal data. However, the distributed nature of FL and the unvetted participants' data makes it vulnerable to backdoor attacks. In these attacks, adversaries inject malicious functionality into the centralized model during training, leading to intentional misclassifications for specific adversary-chosen inputs. While previous research has demonstrated successful injections of persistent backdoors in FL, the persistence also poses a challenge, as their existence in the centralized model can prompt the central aggregation server to take preventive measures to penalize the adversaries. Therefore, this paper proposes a methodology that enables adversaries to effectively remove backdoors from the centralized model upon achieving their objectives or upon suspicion of possible detection. The proposed approach extends the concept of machine unlearning and presents strategies to preserve the performance of the centralized model and simultaneously prevent over-unlearning of information unrelated to backdoor patterns, making the adversaries stealthy while removing backdoors. To the best of our knowledge, this is the first work that explores machine unlearning in FL to remove backdoors to the benefit of adversaries. Exhaustive evaluation considering image classification scenarios demonstrates the efficacy of the proposed method in efficient backdoor removal from the centralized model, injected by state-of-the-art attacks across multiple configurations.

cs.LG↗