arXiv subjects

Rasha Karakchi

Publications and source records attributed to Rasha Karakchi.

10 recordsLinked to original sources

arXiv2026

Hardware-Accelerated Line-Rate Bitstream Screening for Secure FPGA Reconfiguration

As Field-Programmable Gate Arrays (FPGAs) scale in multi-tenant cloud and edge-AI environments, the configuration bitstream has become a critical, yet opaque, security boundary. Existing hardware Trojan detection methods often rely on trusted design artifacts or computationally intensive reverse-engineering, introducing prohibitive latencies in dynamic, "just-in-time" reconfiguration workflows. This paper presents BLADEI (Bitstream-Level Abnormality Detection for Embedded Inference), a bitstream-level security framework designed for deployment-time screening of FPGA configurations without requiring source code, netlists, or vendor-specific tooling. BLADEI introduces a hybrid architecture that combines multi-scale byte-sequence learning with compact statistical representations to detect anomalous configurations directly from raw bitstreams. We implement the framework on a Xilinx PYNQ-Z1 system, demonstrating an end-to-end cloud-to-edge pipeline that enforces security prior to FPGA configuration. Evaluating across 1,383 bitstreams, BLADEI achieves a macro F1-score of 0.91. However, our systems-level characterization reveals a "preprocessing wall": software-based feature extraction accounts for 92% of the total 16.4-second latency, while model inference requires only 1.4 seconds. To address this bottleneck, we propose a streaming hardware-accelerated feature extraction engine designed for the FPGA programmable logic (PL). The evaluation shows that PL-based streaming engine can reduce feature-extraction latency to the millisecond range. This work positions bitstream-level screening as a first-class primitive and demonstrates that hardware-accelerated preprocessing is the key enabler for securing next-generation reconfigurable custom computing machines at line rate.

cs.CR↗

arXiv2026

Machine Learning-Based Graph Simplification for Symbolic Accelerators

Graph-based accelerators have been widely adopted in symbolic data processing applications such as genomics, cybersecurity, and artificial intelligence. However, these systems often suffer from excessive memory usage and inefficiencies stemming from redundant graph structures. We present AutoSlim, a machine learning-based framework that leverages data-driven methods to prune automata graphs for hardware accelerators. Using features extracted from prior graph executions and a Random Forest classifier, AutoSlim identifies and removes low-impact nodes and edges. When applied to a Non-deterministic Finite Automata overlay architecture (NAPOLY+), AutoSlim reduces FPGA resource usage by up to 40%, with corresponding improvements in throughput and power efficiency. The framework includes a verification step to ensure functional equivalence after pruning and suggests promising directions for both hardware optimization and security.

cs.LG↗

arXiv2025

Real-time ML-based Defense Against Malicious Payload in Reconfigurable Embedded Systems

The growing use of FPGAs in reconfigurable systems introducessecurity risks through malicious bitstreams that could cause denial-of-service (DoS), data leakage, or covert attacks. We investigated chip-level hardware malicious payload in embedded systems and proposed a supervised machine learning method to detect malicious bitstreams via static byte-level features. Our approach diverges from existing methods by analyzing bitstreams directly at the binary level, enabling real-time detection without requiring access to source code or netlists. Bitstreams were sourced from state-of-the-art (SOTA) benchmarks and re-engineered to target the Xilinx PYNQ-Z1 FPGA Development Board. Our dataset included 122 samples of benign and malicious configurations. The data were vectorized using byte frequency analysis, compressed using TSVD, and balanced using SMOTE to address class imbalance. The evaluated classifiers demonstrated that Random Forest achieved a macro F1-score of 0.97, underscoring the viability of real-time Trojan detection on resource-constrained systems. The final model was serialized and successfully deployed via PYNQ to enable integrated bitstream analysis.

cs.CR↗

arXiv2025

Hybrid Cryptographic Monitoring System for Side-Channel Attack Detection on PYNQ SoCs

AES-128 encryption is theoretically secure but vulnerable in practical deployments due to timing and fault injection attacks on embedded systems. This work presents a lightweight dual-detection framework combining statistical thresholding and machine learning (ML) for real-time anomaly detection. By simulating anomalies via delays and ciphertext corruption, we collect timing and data features to evaluate two strategies: (1) a statistical threshold method based on execution time and (2) a Random Forest classifier trained on block-level anomalies. Implemented on CPU and FPGA (PYNQ-Z1), our results show that the ML approach outperforms static thresholds in accuracy, while maintaining real-time feasibility on embedded platforms. The framework operates without modifying AES internals or relying on hardware performance counters. This makes it especially suitable for low-power, resource-constrained systems where detection accuracy and computational efficiency must be balanced.

cs.CR↗

arXiv2025

ML-Based Automata Simplification for Symbolic Accelerators

Symbolic accelerators are increasingly used for symbolic data processing in domains such as genomics, NLP, and cybersecurity. However, these accelerators face scalability issues due to excessive memory use and routing complexity, especially when targeting a large set. We present AutoSlim, a machine learning-based graph simplification framework designed to reduce the complexity of symbolic accelerators built on Non-deterministic Finite Automata (NFA) deployed on FPGA-based overlays such as NAPOLY+. AutoSlim uses Random Forest classification to prune low-impact transitions based on edge scores and structural features, significantly reducing automata graph density while preserving semantic correctness. Unlike prior tools, AutoSlim targets automated score-aware simplification with weighted transitions, enabling efficient ranking-based sequence analysis. We evaluated data sets (1K to 64K nodes) in NAPOLY+ and conducted performance measurements including latency, throughput, and resource usage. AutoSlim achieves up to 40 percent reduction in FPGA LUTs and over 30 percent pruning in transitions, while scaling to graphs an order of magnitude larger than existing benchmarks. Our results also demonstrate how hardware interconnection (fanout) heavily influences hardware cost and that AutoSlim's pruning mitigates resource blowup.

cs.LG↗

arXiv2025

ML-Enhanced AES Anomaly Detection for Real-Time Embedded Security

Advanced Encryption Standard (AES) is a widely adopted cryptographic algorithm, yet its practical implementations remain susceptible to side-channel and fault injection attacks. In this work, we propose a comprehensive framework that enhances AES-128 encryption security through controlled anomaly injection and real-time anomaly detection using both statistical and machine learning (ML) methods. We simulate timing and fault-based anomalies by injecting execution delays and ciphertext perturbations during encryption, generating labeled datasets for detection model training. Two complementary detection mechanisms are developed: a threshold-based timing anomaly detector and a supervised Random Forest classifier trained on combined timing and ciphertext features. We implement and evaluate the framework on both CPU and FPGA-based SoC hardware (PYNQ-Z1), measuring performance across varying block sizes, injection rates, and core counts. Our results show that ML-based detection significantly outperforms threshold-based methods in precision and recall while maintaining real-time performance on embedded hardware. Compared to existing AES anomaly detection methods, our solution offers a low-cost, real-time, and accurate detection approach deployable on lightweight FPGA platforms.

cs.CR↗

arXiv2025

Toward a Lightweight, Scalable, and Parallel Secure Encryption Engine

The exponential growth of Internet of Things (IoT) applications has intensified the demand for efficient, high-throughput, and energy-efficient data processing at the edge. Conventional CPU-centric encryption methods suffer from performance bottlenecks and excessive data movement, especially in latency-sensitive and resource-constrained environments. In this paper, we present SPiME, a lightweight, scalable, and FPGA-compatible Secure Processor-in-Memory Encryption architecture that integrates the Advanced Encryption Standard (AES-128) directly into a Processing-in-Memory (PiM) framework. SPiME is designed as a modular array of parallel PiM units, each combining an AES core with a minimal control unit to enable distributed in-place encryption with minimal overhead. The architecture is fully implemented in Verilog and tested on multiple AMD UltraScale and UltraScale+ FPGAs. Evaluation results show that SPiME can scale beyond 4,000 parallel units while maintaining less than 5\% utilization of key FPGA resources on high-end devices. It delivers over 25~Gbps in sustained encryption throughput with predictable, low-latency performance. The design's portability, configurability, and resource efficiency make it a compelling solution for secure edge computing, embedded cryptographic systems, and customizable hardware accelerators.

cs.CR↗

arXiv2025

AI-Driven Optimization of Hardware Overlay Configurations

Designing and optimizing FPGA overlays is a complex and time-consuming process, often requiring multiple trial-and-error iterations to determine a suitable configuration. This paper presents an AI-driven approach to optimizing FPGA overlay configurations, specifically focusing on the NAPOLY+ automata processor implemented on the ZCU104 FPGA. By leveraging machine learning techniques, particularly Random Forest regression, we predict the feasibility and efficiency of different configurations before hardware compilation. Our method significantly reduces the number of required iterations by estimating resource utilization, including logical elements, distributed memory, and fanout, based on historical design data. Experimental results demonstrate that our model achieves high prediction accuracy, closely matching actual resource usage while accelerating the design process.

cs.LG↗

arXiv2025

Optimizing Sequence Alignment with Scored NFAs

The rapid increase in symbolic data has underscored the significance of pattern matching and regular expression processing. While nondeterministic finite automata (NFA) are commonly used for these tasks, they are limited to detecting matches without determining the optimal one. This research expands on the NAPOLY pattern-matching accelerator by introducing NAPOLY+, which adds registers to each processing element to store variables like scores, weights, or edge costs. This enhancement allows NAPOLY+ to identify the highest score corresponding to the best match in sequence alignment tasks through the new-added arithmetic unit in each processor element. The design was evaluated against the original NAPOLY, with results showing that NAPOLY+ offers superior functionality and improved performance in identifying the best match. The design was implemented and tested on zynq102 and zynq104 FPGA devices, with performance metrics compared across array sizes from 1K to 64K processing elements. The results showed that memory usage increased proportionally with array size with Fmax decreasing as the array size grew on both platforms. The reported findings focus specifically on the core array, excluding the impact of buffers and DRAMs.

cs.ET↗

arXiv2024

Developing a Self-Explanatory Transformer

While IoT devices provide significant benefits, their rapid growth results in larger data volumes, increased complexity, and higher security risks. To manage these issues, techniques like encryption, compression, and mapping are used to process data efficiently and securely. General-purpose and AI platforms handle these tasks well, but mapping in natural language processing is often slowed by training times. This work explores a self-explanatory, training-free mapping transformer based on non-deterministic finite automata, designed for Field-Programmable Gate Arrays (FPGAs). Besides highlighting the advantages of this proposed approach in providing real-time, cost-effective processing and dataset-loading, we also address the challenges and considerations for enhancing the design in future iterations.

cs.CR↗