NetDeTox: Adversarial and Efficient Evasion of Hardware-Security GNNs via RL-LLM Orchestration

• URL: http://arxiv.org/abs/2512.00119v1
• Date: Thu, 27 Nov 2025 20:45:00 GMT
• Title: NetDeTox: Adversarial and Efficient Evasion of Hardware-Security GNNs via RL-LLM Orchestration
• Abstract summary: Graph neural networks (GNNs) have shown promise in hardware security by learning structural motifs from netlist graphs.<n>Existing adversarial approaches come with high design overheads.<n>We present NetDeTox, an automated end-to-end framework that orchestrates large language models with reinforcement learning.
• Score: 15.247199764527629
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph neural networks (GNNs) have shown promise in hardware security by learning structural motifs from netlist graphs. However, this reliance on motifs makes GNNs vulnerable to adversarial netlist rewrites; even small-scale edits can mislead GNN predictions. Existing adversarial approaches, ranging from synthesis-recipe perturbations to gate transformations, come with high design overheads. We present NetDeTox, an automated end-to-end framework that orchestrates large language models (LLMs) with reinforcement learning (RL) in a systematic manner, enabling focused local rewriting. The RL agent identifies netlist components critical for GNN-based reasoning, while the LLM devises rewriting plans to diversify motifs that preserve functionality. Iterative feedback between the RL and LLM stages refines adversarial rewritings to limit overheads. Compared to the SOTA work AttackGNN, NetDeTox successfully degrades the effectiveness of all security schemes with fewer rewrites and substantially lower area overheads (reductions of 54.50% for GNN-RE, 25.44% for GNN4IP, and 41.04% for OMLA, respectively). For GNN4IP, ours can even optimize/reduce the original benchmarks' area, in particular for larger circuits, demonstrating the practicality and scalability of NetDeTox.

Related papers

• Reducing ANN-SNN Conversion Error via Residual Membrane Potential Alignment [52.910770415431244]
  Spiking Neural Networks (SNNs) serve as core architectures for neuromorphic computing.<n>ANN-SNN conversion circumvents issues by reusing well-trained ANN weights for low-latency, energy-efficient inference.<n>Existing conversion schemes suffer from severe accuracy drops at small timesteps, large inference delays and cumulative quantization errors.
  arXiv  Detail & Related papers  (2026-08-14T04:46:03Z)
• Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors [10.361566017170295]
  We present a comprehensive analysis of GNN robustness against bit-flip errors.<n>We propose Ralts, a generalizable and lightweight solution to bolster GNN resilience to bit-flip errors.<n>Ralts exploits various graph similarity metrics to filter out outliers and recover compromised graph topology.
  arXiv  Detail & Related papers  (2025-07-24T21:03:44Z)
• Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control [59.65431931190187]
  Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision making on neuromorphic hardware.<n>Most continuous control algorithms for continuous control are designed for Artificial Neural Networks (ANNs)<n>We show that this mismatch destabilizes SNN training and degrades performance.<n>We propose a novel proxy target framework to bridge the gap between discrete SNNs and continuous-control algorithms.
  arXiv  Detail & Related papers  (2025-05-30T03:08:03Z)
• $β$-GNN: A Robust Ensemble Approach Against Graph Structure Perturbation [5.58640026830983]
  Graph Neural Networks (GNNs) are playing an increasingly important role in the efficient operation and security of computing systems.<n>We propose $beta$-GNN, a model enhancing GNN robustness without sacrificing clean data performance.
  arXiv  Detail & Related papers  (2025-03-26T15:24:07Z)
• Grimm: A Plug-and-Play Perturbation Rectifier for Graph Neural Networks Defending against Poisoning Attacks [53.972077392749185]
  Recent studies have revealed the vulnerability of graph neural networks (GNNs) to adversarial poisoning attacks on node classification tasks.<n>Here we introduce Grimm, the first plug-and-play defense model.
  arXiv  Detail & Related papers  (2024-12-11T17:17:02Z)
• Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks? [45.55125612241908]
  Graph neural networks (GNNs) are vulnerable to adversarial attacks, especially for topology perturbations.<n>We propose an LLM-based robust graph structure inference framework, LLM4RGNN.
  arXiv  Detail & Related papers  (2024-08-16T11:58:34Z)
• Securing Graph Neural Networks in MLaaS: A Comprehensive Realization of Query-based Integrity Verification [68.86863899919358]
  We introduce a groundbreaking approach to protect GNN models in Machine Learning from model-centric attacks. Our approach includes a comprehensive verification schema for GNN's integrity, taking into account both transductive and inductive GNNs. We propose a query-based verification technique, fortified with innovative node fingerprint generation algorithms.
  arXiv  Detail & Related papers  (2023-12-13T03:17:05Z)
• Certified Defense on the Fairness of Graph Neural Networks [86.14235652889242]
  Graph Neural Networks (GNNs) have emerged as a prominent graph learning model in various graph-based tasks.<n> malicious attackers could easily corrupt the fairness level of their predictions by adding perturbations to the input graph data.<n>We propose a principled framework named ELEGANT to study a novel problem of certifiable defense on the fairness level of GNNs.
  arXiv  Detail & Related papers  (2023-11-05T20:29:40Z)
• Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience [50.460555688927826]
  We propose the Graph Agent Network (GAgN) to address the vulnerabilities of graph neural networks (GNNs)<n>GAgN is a graph-structured agent network in which each node is designed as an 1-hop-view agent.<n>Agents' limited view prevents malicious messages from propagating globally in GAgN, thereby resisting global-optimization-based secondary attacks.
  arXiv  Detail & Related papers  (2023-06-12T07:27:31Z)
• Robustness of Graph Neural Networks at Scale [63.45769413975601]
  We study how to attack and defend Graph Neural Networks (GNNs) at scale. We propose two sparsity-aware first-order optimization attacks that maintain an efficient representation. We show that common surrogate losses are not well-suited for global attacks on GNNs.
  arXiv  Detail & Related papers  (2021-10-26T21:31:17Z)
• Edge Rewiring Goes Neural: Boosting Network Resilience via Policy Gradient [62.660451283548724]
  ResiNet is a reinforcement learning framework to discover resilient network topologies against various disasters and attacks. We show that ResiNet achieves a near-optimal resilience gain on multiple graphs while balancing the utility, with a large margin compared to existing approaches.
  arXiv  Detail & Related papers  (2021-10-18T06:14:28Z)

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.