SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design

• URL: http://arxiv.org/abs/2506.02089v3
• Date: Tue, 05 Aug 2025 08:08:15 GMT
• Title: SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design
• Authors: Zeng Wang, Minghao Shao, Rupesh Karn, Likhitha Mankali, Jitendra Bhandari, Ramesh Karri, Ozgur Sinanoglu, Muhammad Shafique, Johann Knechtel,
• Abstract summary: Large Language Models (LLMs) offer transformative capabilities for hardware design automation.<n>LLMs pose significant data security challenges, including Verilog evaluation data contamination, intellectual property (IP) design leakage, and the risk of malicious Verilog generation.<n>We introduce SALAD, a comprehensive assessment that leverages machine unlearning to mitigate these threats.
• Score: 15.02451323284475
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) offer transformative capabilities for hardware design automation, particularly in Verilog code generation. However, they also pose significant data security challenges, including Verilog evaluation data contamination, intellectual property (IP) design leakage, and the risk of malicious Verilog generation. We introduce SALAD, a comprehensive assessment that leverages machine unlearning to mitigate these threats. Our approach enables the selective removal of contaminated benchmarks, sensitive IP and design artifacts, or malicious code patterns from pre-trained LLMs, all without requiring full retraining. Through detailed case studies, we demonstrate how machine unlearning techniques effectively reduce data security risks in LLM-aided hardware design.

Related papers

• A Survey on Model Extraction Attacks and Defenses for Large Language Models [55.60375624503877]
  Model extraction attacks pose significant security threats to deployed language models.<n>This survey provides a comprehensive taxonomy of extraction attacks and defenses, categorizing attacks into functionality extraction, training data extraction, and prompt-targeted attacks.<n>We examine defense mechanisms organized into model protection, data privacy protection, and prompt-targeted strategies, evaluating their effectiveness across different deployment scenarios.
  arXiv  Detail & Related papers  (2025-06-26T22:02:01Z)
• Large Language Model Unlearning for Source Code [65.42425213605114]
  PROD is a novel unlearning approach that enables LLMs to forget undesired code content while preserving their code generation capabilities.<n>Our evaluation demonstrates that PROD achieves superior balance between forget quality and model utility compared to existing unlearning approaches.
  arXiv  Detail & Related papers  (2025-06-20T16:27:59Z)
• Does Machine Unlearning Truly Remove Model Knowledge? A Framework for Auditing Unlearning in LLMs [58.24692529185971]
  We introduce a comprehensive auditing framework for unlearning evaluation comprising three benchmark datasets, six unlearning algorithms, and five prompt-based auditing methods.<n>We evaluate the effectiveness and robustness of different unlearning strategies.
  arXiv  Detail & Related papers  (2025-05-29T09:19:07Z)
• LLMpatronous: Harnessing the Power of LLMs For Vulnerability Detection [0.0]
  Large Language Models (LLMs) for vulnerability detection presents unique challenges.<n>Previous attempts employing machine learning models for vulnerability detection have proven ineffective.<n>We propose a robust AI-driven approach focused on mitigating these limitations.
  arXiv  Detail & Related papers  (2025-04-25T15:30:40Z)
• Hardware Design and Security Needs Attention: From Survey to Path Forward [8.165279651848923]
  Recent advances in attention-based artificial intelligence (AI) models have unlocked vast potential to automate digital hardware design.<n>This study explores the commercial and academic landscape, highlighting technical hurdles and future prospects for automating hardware design and security.
  arXiv  Detail & Related papers  (2025-04-11T03:48:57Z)
• Multi-Faceted Studies on Data Poisoning can Advance LLM Development [45.53752823903236]
  This paper proposes rethinking the role of data poisoning in large language models.<n>From a threat perspective, practical strategies for data poisoning attacks can help evaluate and address real safety risks.<n>From a trustworthiness perspective, data poisoning can be leveraged to build more robust LLMs.
  arXiv  Detail & Related papers  (2025-02-20T01:19:51Z)
• Computational Safety for Generative AI: A Signal Processing Perspective [65.268245109828]
  computational safety is a mathematical framework that enables the quantitative assessment, formulation, and study of safety challenges in GenAI.<n>We show how sensitivity analysis and loss landscape analysis can be used to detect malicious prompts with jailbreak attempts.<n>We discuss key open research challenges, opportunities, and the essential role of signal processing in computational AI safety.
  arXiv  Detail & Related papers  (2025-02-18T02:26:50Z)
• Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond [41.3029262040131]
  We investigate how to make unlearned models robust against relearning attacks.<n>Our analysis reveals that smoothness optimization plays a pivotal role in mitigating relearning attacks.
  arXiv  Detail & Related papers  (2025-02-07T23:03:55Z)
• Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities [1.0974825157329373]
  This paper provides a comprehensive review of the future of cybersecurity through Generative AI and Large Language Models (LLMs)<n>We explore LLM applications across various domains, including hardware design security, intrusion detection, software engineering, design verification, cyber threat intelligence, malware detection, and phishing detection.<n>We present an overview of LLM evolution and its current state, focusing on advancements in models such as GPT-4, GPT-3.5, Mixtral-8x7B, BERT, Falcon2, and LLaMA.
  arXiv  Detail & Related papers  (2024-05-21T13:02:27Z)
• Evolutionary Large Language Models for Hardware Security: A Comparative Survey [0.4642370358223669]
  This study explores the seeds of Large Language Models (LLMs) integration in register transfer level (RTL) designs. LLMs can be harnessed to automatically rectify security-relevant vulnerabilities inherent in HW designs.
  arXiv  Detail & Related papers  (2024-04-25T14:42:12Z)
• All Artificial, Less Intelligence: GenAI through the Lens of Formal Verification [2.015768713390138]
  This paper focuses on the formal verification of Common Weaknessions (CWEs) in modern hardware designs. We apply formal verification to categorize each hardware design as vulnerable or CWE-free. We have associated the identified vulnerabilities with CWE numbers for a dataset of 60,000 generated SystemVerilog Register Transfer Level (RTL) code.
  arXiv  Detail & Related papers  (2024-03-25T13:23:24Z)
• The Frontier of Data Erasure: Machine Unlearning for Large Language Models [56.26002631481726]
  Large Language Models (LLMs) are foundational to AI advancements. LLMs pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information. Machine unlearning emerges as a cutting-edge solution to mitigate these concerns.
  arXiv  Detail & Related papers  (2024-03-23T09:26:15Z)
• A Framework for Evaluating the Cybersecurity Risk of Real World, Machine Learning Production Systems [41.470634460215564]
  We develop an extension to the MulVAL attack graph generation and analysis framework to incorporate cyberattacks on ML production systems. Using the proposed extension, security practitioners can apply attack graph analysis methods in environments that include ML components.
  arXiv  Detail & Related papers  (2021-07-05T05:58:11Z)

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.