On the Vulnerability of Deep Automatic Modulation Classifiers to Explainable Backdoor Threats

• URL: http://arxiv.org/abs/2603.25310v1
• Date: Thu, 26 Mar 2026 10:57:00 GMT
• Title: On the Vulnerability of Deep Automatic Modulation Classifiers to Explainable Backdoor Threats
• Abstract summary: Deep learning (DL) has been widely studied for assisting applications of modern wireless communications.<n>One of the applications is automatic modulation classification (AMC)<n>One of the most persistent and stealthy threats is the backdoor (Trojan) attack.
• Score: 0.6989900669395945
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning (DL) has been widely studied for assisting applications of modern wireless communications. One of the applications is automatic modulation classification (AMC). However, DL models are found to be vulnerable to adversarial machine learning (AML) threats. One of the most persistent and stealthy threats is the backdoor (Trojan) attack. Nevertheless, most studied threats originate from other AI domains, such as computer vision (CV). Therefore, in this paper, a physical backdoor attack targeting the wireless signal before transmission is studied. The adversary is considered to be using explainable AI (XAI) to guide the placement of the trigger in the most vulnerable parts of the signal. Then, a class prototype combined with principal components is used to generate the trigger. The studied threat was found to be efficient in breaching multiple DL-based AMC models. The attack achieves high success rates for a wide range of SNR values and a small poisoning ratio.

Related papers

• Physical Backdoor Attack Against Deep Learning-Based Modulation Classification [0.6989900669395945]
  We study a physical backdoor (Trojan) attack that targets a Deep Learning-based modulation classifier.<n>During training, the adversary manipulates amplitudes of RF signals and changes their labels to a target modulation scheme, training a backdoored model.<n>We demonstrate that our proposed attack achieves high attack success rates with few manipulated RD signals for different noise levels.
  arXiv  Detail & Related papers  (2026-03-26T10:49:07Z)
• Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols [80.68060125494645]
  We study adaptive attacks by an untrusted model that knows the protocol and the monitor model.<n>We instantiate a simple adaptive attack vector by which the attacker embeds publicly known or zero-shot prompt injections in the model outputs.
  arXiv  Detail & Related papers  (2025-10-10T15:12:44Z)
• TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models [67.06525001375722]
  TrojanTO is the first action-level backdoor attack against TO models.<n>It implants backdoor attacks across diverse tasks and attack objectives with a low attack budget.<n>TrojanTO exhibits broad applicability to DT, GDT, and DC.
  arXiv  Detail & Related papers  (2025-06-15T11:27:49Z)
• 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)
• VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models [65.23688155159398]
  Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed to further enhance instruction-following abilities. Adversaries can implant a backdoor by injecting poisoned samples with triggers embedded in instructions or images. We propose a multimodal instruction backdoor attack, namely VL-Trojan.
  arXiv  Detail & Related papers  (2024-02-21T14:54:30Z)
• A Unified Hardware-based Threat Detector for AI Accelerators [12.96840649714218]
  We design UniGuard, a novel unified and non-intrusive detection methodology to safeguard FPGA-based AI accelerators. We employ a Time-to-Digital Converter to capture power fluctuations and train a supervised machine learning model to identify various types of threats.
  arXiv  Detail & Related papers  (2023-11-28T10:55:02Z)
• Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment [31.24530091590395]
  We study an attack scenario called Trojan Activation Attack (TA2), which injects trojan steering vectors into the activation layers of Large Language Models. Our experiment results show that TA2 is highly effective and adds little or no overhead to attack efficiency.
  arXiv  Detail & Related papers  (2023-11-15T23:07:40Z)
• Attention-Enhancing Backdoor Attacks Against BERT-based Models [54.070555070629105]
  Investigating the strategies of backdoor attacks will help to understand the model's vulnerability. We propose a novel Trojan Attention Loss (TAL) which enhances the Trojan behavior by directly manipulating the attention patterns.
  arXiv  Detail & Related papers  (2023-10-23T01:24:56Z)
• 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)
• Downlink Power Allocation in Massive MIMO via Deep Learning: Adversarial Attacks and Training [62.77129284830945]
  This paper considers a regression problem in a wireless setting and shows that adversarial attacks can break the DL-based approach. We also analyze the effectiveness of adversarial training as a defensive technique in adversarial settings and show that the robustness of DL-based wireless system against attacks improves significantly.
  arXiv  Detail & Related papers  (2022-06-14T04:55:11Z)
• Adversarial defense for automatic speaker verification by cascaded self-supervised learning models [101.42920161993455]
  More and more malicious attackers attempt to launch adversarial attacks at automatic speaker verification (ASV) systems. We propose a standard and attack-agnostic method based on cascaded self-supervised learning models to purify the adversarial perturbations. Experimental results demonstrate that the proposed method achieves effective defense performance and can successfully counter adversarial attacks.
  arXiv  Detail & Related papers  (2021-02-14T01:56:43Z)
• Binary Black-box Evasion Attacks Against Deep Learning-based Static Malware Detectors with Adversarial Byte-Level Language Model [11.701290164823142]
  MalRNN is a novel approach to automatically generate evasive malware variants without restrictions. MalRNN effectively evades three recent deep learning-based malware detectors and outperforms current benchmark methods.
  arXiv  Detail & Related papers  (2020-12-14T22:54:53Z)

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.