NuRedact: Non-Uniform eFPGA Architecture for Low-Overhead and Secure IP Redaction

• URL: http://arxiv.org/abs/2601.11770v1
• Date: Fri, 16 Jan 2026 20:55:30 GMT
• Title: NuRedact: Non-Uniform eFPGA Architecture for Low-Overhead and Secure IP Redaction
• Authors: Voktho Das, Kimia Azar, Hadi Kamali,
• Abstract summary: This paper introduces NuRedact, the first full-custom eFPGA redaction framework that embraces architectural non-uniformity to balance security and efficiency.<n>From a security perspective, NuRedact fabrics are evaluated against state-of-the-art attack models, including SAT-based, cyclic, and sequential variants, and show enhanced resilience while maintaining practical design overheads.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While logic locking has been extensively studied as a countermeasure against integrated circuit (IC) supply chain threats, recent research has shifted toward reconfigurable-based redaction techniques, e.g., LUT- and eFPGA-based schemes. While these approaches raise the bar against attacks, they incur substantial overhead, much of which arises not from genuine functional reconfigurability need, but from artificial complexity intended solely to frustrate reverse engineering (RE). As a result, fabrics are often underutilized, and security is achieved at disproportionate cost. This paper introduces NuRedact, the first full-custom eFPGA redaction framework that embraces architectural non-uniformity to balance security and efficiency. Built as an extension of the widely adopted OpenFPGA infrastructure, NuRedact introduces a three-stage methodology: (i) custom fabric generation with pin-mapping irregularity, (ii) VPR-level modifications to enable non-uniform placement guided by an automated Python-based optimizer, and (iii) redaction-aware reconfiguration and mapping of target IP modules. Experimental results show up to 9x area reduction compared to conventional uniform fabrics, achieving competitive efficiency with LUT-based and even transistor-level redaction techniques while retaining strong resilience. From a security perspective, NuRedact fabrics are evaluated against state-of-the-art attack models, including SAT-based, cyclic, and sequential variants, and show enhanced resilience while maintaining practical design overheads.

Related papers

• SpanNorm: Reconciling Training Stability and Performance in Deep Transformers [55.100133502295996]
  We propose SpanNorm, a novel technique designed to resolve the dilemma by integrating the strengths of both paradigms.<n>We provide a theoretical analysis demonstrating that SpanNorm, combined with a principled scaling strategy, maintains bounded signal variance throughout the network.<n> Empirically, SpanNorm consistently outperforms standard normalization schemes in both dense and Mixture-of-Experts (MoE) scenarios.
  arXiv  Detail & Related papers  (2026-01-30T05:21:57Z)
• A Multi-Stage Optimization Framework for Deploying Learned Image Compression on FPGAs [7.577235739757108]
  Deep learning-based image compression (LIC) has achieved state-of-the-art rate-distortion (RD) performance, yet deploying these models on resource-constrained FPGAs remains a major challenge.<n>This work presents a complete, multi-stage optimization framework to bridge the gap between high-performance floating-point models and efficient, hardware-friendly integer-based implementations.
  arXiv  Detail & Related papers  (2025-11-21T10:55:44Z)
• Logic-informed reinforcement learning for cross-domain optimization of large-scale cyber-physical systems [7.352750348429755]
  We present logic-informed reinforcement learning (LIRL) for cyber-physical systems.<n>LIRL maps a low-dimensional latent action onto the admissible hybrid manifold defined on-the-fly by first-order logic.<n>It consistently maintains zero constraint violations and significantly surpasses state-of-the-art hybrid-action reinforcement learning baselines.
  arXiv  Detail & Related papers  (2025-11-02T05:02:17Z)
• FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Models [7.085700272776079]
  Forget and Rewire (FaR) methodology has demonstrated strong resilience against Bit-Flip Attacks (BFAs) on Transformer-based models.<n>We propose FaRAccel, a novel hardware accelerator architecture implemented on FPGA, specifically designed to offload and optimize FaR operations.<n>FaRAccel integrates reconfigurable logic for dynamic activation rerouting, and lightweight storage of rewiring configurations, enabling low-latency inference with minimal energy overhead.
  arXiv  Detail & Related papers  (2025-10-28T21:27:09Z)
• Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness [9.013874391203453]
  Adversarial examples reveal critical vulnerabilities in deep neural networks by exploiting their sensitivity to imperceptible input perturbations.<n>In this work, we investigate an architectural approach to adversarial robustness by embedding group-equivariant convolutions.<n>These layers encode symmetry priors that align model behavior with structured transformations in the input space, promoting smoother decision boundaries.
  arXiv  Detail & Related papers  (2025-10-17T19:26:58Z)
• Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization [49.32786615205064]
  Split Inference (SI) partitions computation between edge devices and the cloud to reduce latency and protect user privacy.<n>Recent advances in Data Reconstruction Attacks (DRAs) reveal that intermediate features exchanged in SI can be exploited to recover sensitive input data.<n>Existing DRAs are typically effective only on shallow models and fail to fully leverage semantic priors.<n>We propose a novel GAN-based DRA framework with Progressive Feature Optimization (PFO), which decomposes the generator into hierarchical blocks and incrementally refines intermediate representations to enhance the semantic fidelity of reconstructed images.
  arXiv  Detail & Related papers  (2025-08-28T10:00:39Z)
• Designing with Deception: ML- and Covert Gate-Enhanced Camouflaging to Thwart IC Reverse Engineering [2.6217304977339473]
  Integrated circuits (ICs) are essential to modern electronic systems, yet they face significant risks from physical reverse engineering (RE) attacks.<n>We present a machine learning-driven methodology that integrates cryptic and mimetic cyber deception principles to enhance IC security against RE.<n>Our work sets a new standard for IC camouflage, advancing the application of cyber deception principles to protect critical systems from adversarial threats.
  arXiv  Detail & Related papers  (2025-08-11T20:40:42Z)
• REFINE: Inversion-Free Backdoor Defense via Model Reprogramming [60.554146386198376]
  Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat.<n>We propose REFINE, an inversion-free backdoor defense method based on model reprogramming.
  arXiv  Detail & Related papers  (2025-02-22T07:29:12Z)
• ASR: Attention-alike Structural Re-parameterization [53.019657810468026]
  We propose a simple-yet-effective attention-alike structural re- parameterization (ASR) that allows us to achieve SRP for a given network while enjoying the effectiveness of the attention mechanism. In this paper, we conduct extensive experiments from a statistical perspective and discover an interesting phenomenon Stripe Observation, which reveals that channel attention values quickly approach some constant vectors during training.
  arXiv  Detail & Related papers  (2023-04-13T08:52:34Z)
• IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound [85.6899802468343]
  We present IBP-R, a novel verified training algorithm that is both simple effective. We also present UPB, a novel robustness based on $beta$-CROWN, that reduces the cost state-of-the-art branching algorithms.
  arXiv  Detail & Related papers  (2022-06-29T17:13:25Z)
• ISTR: End-to-End Instance Segmentation with Transformers [147.14073165997846]
  We propose an instance segmentation Transformer, termed ISTR, which is the first end-to-end framework of its kind. ISTR predicts low-dimensional mask embeddings, and matches them with ground truth mask embeddings for the set loss. Benefiting from the proposed end-to-end mechanism, ISTR demonstrates state-of-the-art performance even with approximation-based suboptimal embeddings.
  arXiv  Detail & Related papers  (2021-05-03T06:00:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.