Architectural Backdoors in Deep Learning: A Survey of Vulnerabilities, Detection, and Defense

• URL: http://arxiv.org/abs/2507.12919v1
• Date: Thu, 17 Jul 2025 09:02:54 GMT
• Title: Architectural Backdoors in Deep Learning: A Survey of Vulnerabilities, Detection, and Defense
• Abstract summary: Architectural backdoors embed malicious logic directly into a model's computational graph.<n>This survey consolidates research on architectural backdoors, spanning compiler-level manipulations, tainted AutoML pipelines, and supply-chain vulnerabilities.<n>Despite recent progress, scalable and practical defenses remain elusive.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Architectural backdoors pose an under-examined but critical threat to deep neural networks, embedding malicious logic directly into a model's computational graph. Unlike traditional data poisoning or parameter manipulation, architectural backdoors evade standard mitigation techniques and persist even after clean retraining. This survey systematically consolidates research on architectural backdoors, spanning compiler-level manipulations, tainted AutoML pipelines, and supply-chain vulnerabilities. We assess emerging detection and defense strategies, including static graph inspection, dynamic fuzzing, and partial formal verification, and highlight their limitations against distributed or stealth triggers. Despite recent progress, scalable and practical defenses remain elusive. We conclude by outlining open challenges and proposing directions for strengthening supply-chain security, cryptographic model attestations, and next-generation benchmarks. This survey aims to guide future research toward comprehensive defenses against structural backdoor threats in deep learning systems.

Related papers

• Securing Deep Learning Hardware: A Survey of Side-Channel Vulnerabilities and Countermeasures [0.8602553195689513]
  Deep learning models are increasingly deployed in critical sectors such as healthcare, finance, and security.<n>Side-channel attacks (SCAs) represent a particular challenge since they can extract sensitive information without requiring direct access to the model.<n>By leveraging the physical and micro-architectural properties of the hardware, attackers can compromise systems.
  arXiv  Detail & Related papers  (2026-07-04T23:45:25Z)
• 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)
• Lazarus Group Targets Crypto-Wallets and Financial Data while employing new Tradecrafts [0.0]
  This report presents a comprehensive analysis of a malicious software sample, detailing its architecture, behavioral characteristics, and underlying intent.<n>The malware core functionalities, including persistence mechanisms, command-and-control communication, and data exfiltration routines, are identified.<n>This malware analysis report not only reconstructs past adversary actions but also establishes a robust foundation for anticipating and mitigating future attacks.
  arXiv  Detail & Related papers  (2025-05-27T20:13:29Z)
• PCAP-Backdoor: Backdoor Poisoning Generator for Network Traffic in CPS/IoT Environments [0.6629765271909503]
  We introduce textttPCAP-Backdoor, a novel technique that facilitates backdoor poisoning attacks on PCAP datasets.<n>Experiments on real-world Cyber-Physical Systems (CPS) and Internet of Things (IoT) network traffic datasets demonstrate that attackers can effectively backdoor a model by poisoning as little as 1% or less of the entire training dataset.
  arXiv  Detail & Related papers  (2025-01-26T15:49:34Z)
• A Backdoor Attack Scheme with Invisible Triggers Based on Model Architecture Modification [12.393139669821869]
  Traditional backdoor attacks involve injecting malicious samples with specific triggers into the training data.<n>More sophisticated attacks modify the model's architecture directly.<n>A novel backdoor attack method is presented in the paper.<n>It embeds the backdoor within the model's architecture and has the capability to generate inconspicuous and stealthy triggers.
  arXiv  Detail & Related papers  (2024-12-22T07:39:43Z)
• A Survey and Evaluation of Adversarial Attacks for Object Detection [11.48212060875543]
  Deep learning models are vulnerable to adversarial examples that can deceive them into making confident but incorrect predictions.<n>This vulnerability pose significant risks in high-stakes applications such as autonomous vehicles, security surveillance, and safety-critical inspection systems.<n>This paper presents a novel taxonomic framework for categorizing adversarial attacks specific to object detection architectures.
  arXiv  Detail & Related papers  (2024-08-04T05:22:08Z)
• BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning [85.2564206440109]
  This paper reveals the threats in this practical scenario that backdoor attacks can remain effective even after defenses. We introduce the emphtoolns attack, which is resistant to backdoor detection and model fine-tuning defenses.
  arXiv  Detail & Related papers  (2023-11-20T02:21:49Z)
• Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Survey [114.17568992164303]
  Adrial attacks and defenses in machine learning and deep neural network have been gaining significant attention. This survey provides a comprehensive overview of the recent advancements in the field of adversarial attack and defense techniques. New avenues of attack are also explored, including search-based, decision-based, drop-based, and physical-world attacks.
  arXiv  Detail & Related papers  (2023-03-11T04:19:31Z)
• Untargeted Backdoor Attack against Object Detection [69.63097724439886]
  We design a poison-only backdoor attack in an untargeted manner, based on task characteristics. We show that, once the backdoor is embedded into the target model by our attack, it can trick the model to lose detection of any object stamped with our trigger patterns.
  arXiv  Detail & Related papers  (2022-11-02T17:05:45Z)
• An anomaly detection approach for backdoored neural networks: face recognition as a case study [77.92020418343022]
  We propose a novel backdoored network detection method based on the principle of anomaly detection. We test our method on a novel dataset of backdoored networks and report detectability results with perfect scores.
  arXiv  Detail & Related papers  (2022-08-22T12:14:13Z)
• Backdoor Learning: A Survey [75.59571756777342]
  Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs) Backdoor learning is an emerging and rapidly growing research area. This paper presents the first comprehensive survey of this realm.
  arXiv  Detail & Related papers  (2020-07-17T04:09:20Z)

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.