Hardware Design and Security in the Era of Chiplets and LLMs

• URL: http://arxiv.org/abs/2608.05063v1
• Date: Wed, 05 Aug 2026 17:09:13 GMT
• Title: Hardware Design and Security in the Era of Chiplets and LLMs
• Abstract summary: The semiconductor industry is undergoing a dual revolution: the shift toward heterogeneous 2.5D chiplet systems and the integration of Large Language Models into Electronic Design Automation flows.<n>This paper provides a unified analysis of these frontiers, ranging from attacks on chiplet systems across architectural, logical, and physical levels, to various exploits against LLM-driven EDA pipelines.
• Score: 12.304805014484423
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The semiconductor industry is undergoing a dual revolution: the shift toward heterogeneous 2.5D chiplet systems and the integration of Large Language Models (LLMs) into Electronic Design Automation (EDA) flows. While these paradigms offer unprecedented benefits in yield, modularity, design productivity, etc., they radically expand the hardware attack surface. This paper provides a unified analysis of these frontiers, ranging from attacks on chiplet systems (including hardware stacks for LLM acceleration) across architectural, logical, and physical levels, to various exploits against LLM-driven EDA pipelines. To secure chiplet systems, we review a powerful defense approach that leverages 2.5D split manufacturing and active interposers for physically isolated Root of Trust (RoT) architectures. To secure LLM-driven EDA pipelines, we first identify native threats and then review state-of-the-art defense techniques. Finally, we discuss how LLM systems can advance hardware security efforts for modern systems, including chiplets.

Related papers

• 2.5D Root of Trust: Securing the Chiplet Ecosystem [4.903182581735334]
  semiconductor industry is transitioning from monolithic systems-on-chip to heterogeneous, multi-vendor 2.5D chiplet ecosystems integrated via silicon interposers.<n>Integrating chiplets from untrusted foundries and design houses introduces vulnerabilities to hardware Trojans, IP piracy, and system-level communication exploits.<n>This paper surveys state-of-the-art security strategies for interposer-based 2.5D integration.
  arXiv  Detail & Related papers  (2026-06-20T19:19:54Z)
• MESA: Improving MoE Safety Alignment via Decentralized Expertise [55.2978630005606]
  MESA (MoE Safety Alignment) is a targeted alignment framework for MoE-based Large Language Models.<n>It strategically decentralizes safety responsibility to maximize coverage while minimizing interference with utility.<n>MESA achieves robust defensive performance against varied harmful benchmarks while preserving helpfulness.
  arXiv  Detail & Related papers  (2026-05-30T09:54:38Z)
• LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges [13.013353332008869]
  Large Language Models (LLMs) are being integrated into Electronic Design Automation (EDA) and hardware security.<n>LLMs offer unprecedented capabilities in generating Register Transfer Level (RTL) code, automating testbenches, and bridging the semantic gap between high-level specifications and silicon.<n>This review provides an in-depth analysis of the state-of-the-art in LLM-driven hardware design, organized around key advancements in EDA synthesis, hardware trust, design for security, and education.
  arXiv  Detail & Related papers  (2026-05-11T16:31:14Z)
• Toward a Multi-Layer ML-Based Security Framework for Industrial IoT [5.9556977806856155]
  We present the research framework and contributions of our doctoral thesis, which aims to develop a lightweight, Machine Learning (ML)-based security framework for IIoT environments.<n>We first describe our adoption of the Tm-IIoT trust model and the Hybrid IIoT architecture as foundational baselines, then introduce the Trust Convergence Acceleration (TCA) approach.<n>We then propose a real-world deployment architecture based on affordable, open-source hardware, designed to implement and extend the security framework.
  arXiv  Detail & Related papers  (2026-03-25T09:16:43Z)
• Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography [77.44136793431893]
  We propose a novel jailbreak paradigm that introduces dual steganography to covertly embed malicious queries into benign-looking images.<n>Our Odysseus successfully jailbreaks several pioneering and realistic MLLM-integrated systems, achieving up to 99% attack success rate.
  arXiv  Detail & Related papers  (2025-12-23T08:53:36Z)
• Adversarial Attack-Defense Co-Evolution for LLM Safety Alignment via Tree-Group Dual-Aware Search and Optimization [51.12422886183246]
  Large Language Models (LLMs) have developed rapidly in web services, delivering unprecedented capabilities while amplifying societal risks.<n>Existing works tend to focus on either isolated jailbreak attacks or static defenses, neglecting the dynamic interplay between evolving threats and safeguards in real-world web contexts.<n>We propose ACE-Safety, a novel framework that jointly optimize attack and defense models by seamlessly integrating two key innovative procedures.
  arXiv  Detail & Related papers  (2025-11-24T15:23:41Z)
• Securing Transformer-based AI Execution via Unified TEEs and Crypto-protected Accelerators [19.93096649006403]
  Machine learning runs on untrusted cloud infrastructure, exposing data and models to potential breaches.<n>Running model inference entirely within trusted execution environments (TEEs) is subject to non-trivial slowdown.<n>We propose TwinShield, a framework enabling secure Transformer inference in heterogeneous TEE and accelerator systems.
  arXiv  Detail & Related papers  (2025-07-04T03:52:53Z)
• Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025 [167.94680155673046]
  This report presents findings from the Adversarial Testing & Large-model Alignment Safety Grand Challenge (ATLAS) 2025.<n>The competition involved 86 teams testing MLLM vulnerabilities via adversarial image-text attacks in two phases: white-box and black-box evaluations.<n>The challenge establishes new benchmarks for MLLM safety evaluation and lays groundwork for advancing safer AI systems.
  arXiv  Detail & Related papers  (2025-06-14T10:03:17Z)
• Output Constraints as Attack Surface: Exploiting Structured Generation to Bypass LLM Safety Mechanisms [0.9091225937132784]
  We reveal a critical control-plane attack surface to traditional data-plane vulnerabilities.<n>We introduce Constrained Decoding Attack, a novel jailbreak class that weaponizes structured output constraints to bypass safety mechanisms.<n>Our findings identify a critical security blind spot in current LLM architectures and urge a paradigm shift in LLM safety to address control-plane vulnerabilities.
  arXiv  Detail & Related papers  (2025-03-31T15:08:06Z)
• Safety Guardrails for LLM-Enabled Robots [82.0459036717193]
  Traditional robot safety approaches do not address the novel vulnerabilities of large language models (LLMs)<n>We propose RoboGuard, a two-stage guardrail architecture to ensure the safety of LLM-enabled robots.<n>We show that RoboGuard reduces the execution of unsafe plans from 92% to below 2.5% without compromising performance on safe plans.
  arXiv  Detail & Related papers  (2025-03-10T22:01:56Z)
• A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems [47.18371401090435]
  We analyze the security of Large Language Model (LLM) systems, instead of focusing on the individual LLMs. We propose a multi-layer and multi-step approach and apply it to the state-of-art OpenAI GPT4. We found that although the OpenAI GPT4 has designed numerous safety constraints to improve its safety features, these safety constraints are still vulnerable to attackers.
  arXiv  Detail & Related papers  (2024-02-28T19:00:12Z)
• On the Vulnerability of LLM/VLM-Controlled Robotics [54.57914943017522]
  We highlight vulnerabilities in robotic systems integrating large language models (LLMs) and vision-language models (VLMs) due to input modality sensitivities.<n>Our results show that simple input perturbations reduce task execution success rates by 22.2% and 14.6% in two representative LLM/VLM-controlled robotic systems.
  arXiv  Detail & Related papers  (2024-02-15T22:01:45Z)

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.