Semantic Consensus Decoding: Backdoor Defense for Verilog Code Generation

• URL: http://arxiv.org/abs/2602.04195v1
• Date: Wed, 04 Feb 2026 04:19:49 GMT
• Title: Semantic Consensus Decoding: Backdoor Defense for Verilog Code Generation
• Abstract summary: Large language models (LLMs) for Verilog code generation are increasingly adopted in hardware design.<n>LLMs are vulnerable to backdoor attacks where adversaries inject malicious triggers during training to induce vulnerable hardware designs.<n>We propose Semantic Consensus Decoding (SCD), an inference-time passive defense with two key components.
• Score: 16.148817642071638
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) for Verilog code generation are increasingly adopted in hardware design, yet remain vulnerable to backdoor attacks where adversaries inject malicious triggers during training to induce vulnerable hardware designs. Unlike patchable software vulnerabilities, hardware trojans become irreversible once fabricated, making remediation extremely costly or impossible. Existing active defenses require access to training data, impractical for third-party LLM users, while passive defenses struggle against semantically stealthy triggers that naturally blend into design specifications. In this paper, we hypothesize that under the requirements of both effectiveness and stealthiness, attackers are strongly biased toward embedding triggers in non-functional requirements (e.g., style modifiers, quality descriptors) rather than functional specifications that determine hardware behavior. Exploiting this insight, we propose Semantic Consensus Decoding (SCD), an inference-time passive defense with two key components: (1) functional requirement extraction that identifies essential requirements from user specifications, and (2) consensus decoding that adaptively fuses output distributions based on full user specifications and extracted functional requirements. When these distributions diverge significantly, SCD automatically suppresses suspicious components. Extensive experiments with three representative backdoor attacks demonstrate that SCD reduces average attack success rate from 89% to under 3% with negligible impact on generation quality.

Related papers

• Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions [9.502148118198471]
  We present CodeTracer, a forensic framework that traces malicious code completions back to the backdoor fine-tuning data responsible for them.<n>CodeTracer consistently achieves high forensic accuracy, low false identification rates, and strong robustness against adaptive attacks.
  arXiv  Detail & Related papers  (2026-07-09T00:37:25Z)
• CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents [27.35968236632966]
  LLM-based code interpreter agents are increasingly deployed in critical situations.<n>Existing benchmarks fail to capture the security risks arising from dynamic code execution, tool interactions, and multi-turn context.<n>We introduce CIBER, an automated benchmark that combines dynamic attack generation, isolated secure sandboxing, and state-aware evaluation.
  arXiv  Detail & Related papers  (2026-02-23T06:41:41Z)
• Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation [37.091275561451695]
  Existing backdoor attacks on code models face a fundamental trade-off between transferability and stealthiness.<n>We propose Sharpness-aware Transferable Adversarial Backdoor (STAB)<n>STAB achieves both transferability and stealthiness without requiring complete victim data.
  arXiv  Detail & Related papers  (2026-02-11T08:26:47Z)
• Semantically-Equivalent Transformations-Based Backdoor Attacks against Neural Code Models: Characterization and Mitigation [13.36343806244795]
  We introduce a new kind of backdoor attacks, dubbed Semantically-Equivalent Transformation (SET)-based backdoor attacks.<n>We show that SET-based attacks achieve high success rates (often >90%) while preserving model utility.<n>The attack proves highly stealthy, evading state-of-the-art defenses with detection rates on average over 25.13% lower than injection-based counterparts.
  arXiv  Detail & Related papers  (2025-12-22T09:54:52Z)
• Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain [82.98626829232899]
  Fine-tuning AI agents on data from their own interactions introduces a critical security vulnerability within the AI supply chain.<n>We show that adversaries can easily poison the data collection pipeline to embed hard-to-detect backdoors.
  arXiv  Detail & Related papers  (2025-10-03T12:47:21Z)
• Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security [63.41350337821108]
  We propose Secure Tug-of-War (SecTOW) to enhance the security of multimodal large language models (MLLMs)<n>SecTOW consists of two modules: a defender and an auxiliary attacker, both trained iteratively using reinforcement learning (GRPO)<n>We show that SecTOW significantly improves security while preserving general performance.
  arXiv  Detail & Related papers  (2025-07-29T17:39:48Z)
• Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents [54.35629963816521]
  This work introduces VIBMA, the first clean-text backdoor attack targeting VLM-based mobile agents.<n>The attack injects malicious behaviors into the model by modifying only the visual input.<n>We show that our attack achieves high success rates while preserving clean-task behavior.
  arXiv  Detail & Related papers  (2025-06-16T08:09:32Z)
• DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents [52.92354372596197]
  Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities.<n>This interaction also introduces the risk of prompt injection attacks, where malicious inputs from external sources can mislead the agent's behavior.<n>We propose a Dynamic Rule-based Isolation Framework for Trustworthy agentic systems, which enforces both control and data-level constraints.
  arXiv  Detail & Related papers  (2025-06-13T05:01:09Z)
• GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation [17.36458017234638]
  GUARD is a novel dual-agent defense framework designed to counter CoT backdoor attacks in neural code generation.<n>GUARD integrates two core components: GUARD-Judge, which identifies suspicious CoT steps and potential triggers through comprehensive analysis, and GUARD-Repair, which employs a retrieval-augmented generation approach to regenerate secure CoT steps.
  arXiv  Detail & Related papers  (2025-05-27T16:55:46Z)
• Reformulation is All You Need: Addressing Malicious Text Features in DNNs [53.45564571192014]
  We propose a unified and adaptive defense framework that is effective against both adversarial and backdoor attacks.<n>Our framework outperforms existing sample-oriented defense baselines across a diverse range of malicious textual features.
  arXiv  Detail & Related papers  (2025-02-02T03:39:43Z)
• An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection [17.948513691133037]
  We introduce CodeBreaker, a pioneering LLM-assisted backdoor attack framework on code completion models. By integrating malicious payloads directly into the source code with minimal transformation, CodeBreaker challenges current security measures.
  arXiv  Detail & Related papers  (2024-06-10T22:10:05Z)
• Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing [107.97160023681184]
  Aligned large language models (LLMs) are vulnerable to jailbreaking attacks. We propose SEMANTICSMOOTH, a smoothing-based defense that aggregates predictions of semantically transformed copies of a given input prompt.
  arXiv  Detail & Related papers  (2024-02-25T20:36:03Z)

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.