Trojan Attacks on Neural Network Controllers for Robotic Systems

• URL: http://arxiv.org/abs/2602.05121v1
• Date: Wed, 04 Feb 2026 23:12:22 GMT
• Title: Trojan Attacks on Neural Network Controllers for Robotic Systems
• Abstract summary: This paper investigates backdoor (Trojan) attacks against neural controllers.<n>We design a lightweight, parallel Trojan network that can be embedded within the controller.<n>The results confirm the effectiveness of the proposed attack and demonstrate that neural network-based robotic control systems are subject to potentially critical security threats.
• Score: 0.3823356975862005
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural network controllers are increasingly deployed in robotic systems for tasks such as trajectory tracking and pose stabilization. However, their reliance on potentially untrusted training pipelines or supply chains introduces significant security vulnerabilities. This paper investigates backdoor (Trojan) attacks against neural controllers, using a differential-drive mobile robot platform as a case study. In particular, assuming that the robot's tracking controller is implemented as a neural network, we design a lightweight, parallel Trojan network that can be embedded within the controller. This malicious module remains dormant during normal operation but, upon detecting a highly specific trigger condition defined by the robot's pose and goal parameters, compromises the primary controller's wheel velocity commands, resulting in undesired and potentially unsafe robot behaviours. We provide a proof-of-concept implementation of the proposed Trojan network, which is validated through simulation under two different attack scenarios. The results confirm the effectiveness of the proposed attack and demonstrate that neural network-based robotic control systems are subject to potentially critical security threats.

Related papers

• TrojanWorld: Backdooring World-Model Agents via Imagination Steering [65.38754125569848]
  TrojanWorld is a backdoor framework for world-model agents that induces attacker-specified behavior by steering internal imagination.<n>Under trigger activation, TrojanWorld achieves a target-action deviation as low as 0.026 while retaining at least 98.8% of the corresponding clean performance.
  arXiv  Detail & Related papers  (2026-09-07T05:14:10Z)
• From Prompt to Physical Action: Structured Backdoor Attacks on LLM-Mediated Robotic Control Systems [3.6185608572339962]
  Large language models (LLMs) are integrated into robotic control pipelines to translate user prompts into executable commands.<n>This digital-to-physical interface introduces a critical and underexplored vulnerability: structured backdoor attacks embedded during fine-tuning.<n>We experimentally investigate LoRA-based supply-chain backdoors in LLM-mediated ROS2 robotic control systems and evaluate their impact on physical robot execution.
  arXiv  Detail & Related papers  (2026-04-04T23:06:16Z)
• 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)
• Cybersecurity AI: Humanoid Robots as Attack Vectors [0.448741371377488]
  We present a systematic security assessment of the Unitree G1 humanoid.<n>We show it operates simultaneously as a covert surveillance node and can be purposed as an active cyber operations platform.
  arXiv  Detail & Related papers  (2025-09-17T16:18:53Z)
• Offensive Robot Cybersecurity [0.0]
  The thesis uncovers a profound connection between robotic architecture and cybersecurity.<n>Approaching cybersecurity with a dual perspective of defense and attack has been pivotal.<n>This thesis proposes a novel architecture for cybersecurity cognitive engines.
  arXiv  Detail & Related papers  (2025-06-18T10:49:40Z)
• Model Extraction Attacks Against Reinforcement Learning Based Controllers [9.273077240506016]
  This paper focuses on the setting when a Deep Neural Network (DNN) controller is trained using Reinforcement Learning (RL) algorithms and is used to control a system. In the first phase, also called the offline phase, the attacker uses side-channel information about the RL-reward function and the system dynamics to identify a set of candidate estimates of the unknown DNN. In the second phase, also called the online phase, the attacker observes the behavior of the unknown DNN and uses these observations to shortlist the set of final policy estimates.
  arXiv  Detail & Related papers  (2023-04-25T18:48:42Z)
• FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases [50.065022493142116]
  Trojan attack on deep neural networks, also known as backdoor attack, is a typical threat to artificial intelligence. FreeEagle is the first data-free backdoor detection method that can effectively detect complex backdoor attacks.
  arXiv  Detail & Related papers  (2023-02-28T11:31:29Z)
• Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems [79.07468367923619]
  We propose a backpropagation-free approach to robotic control through the neuro-cognitive computational framework of neural generative coding (NGC) We design an agent built completely from powerful predictive coding/processing circuits that facilitate dynamic, online learning from sparse rewards. We show that our proposed ActPC agent performs well in the face of sparse (extrinsic) reward signals and is competitive with or outperforms several powerful backprop-based RL approaches.
  arXiv  Detail & Related papers  (2022-09-19T16:49:32Z)
• The Feasibility and Inevitability of Stealth Attacks [63.14766152741211]
  We study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence systems. In contrast to adversarial data modification, the attack mechanism we consider here involves alterations to the AI system itself.
  arXiv  Detail & Related papers  (2021-06-26T10:50:07Z)
• Cassandra: Detecting Trojaned Networks from Adversarial Perturbations [92.43879594465422]
  In many cases, pre-trained models are sourced from vendors who may have disrupted the training pipeline to insert Trojan behaviors into the models. We propose a method to verify if a pre-trained model is Trojaned or benign. Our method captures fingerprints of neural networks in the form of adversarial perturbations learned from the network gradients.
  arXiv  Detail & Related papers  (2020-07-28T19:00:40Z)
• Robustness to Adversarial Attacks in Learning-Enabled Controllers [3.4983716329137353]
  We consider state perturbations that encompass a wide variety of adversarial attacks and describe an attack scheme for discovering adversarial states. To be useful, these attacks need to be natural, yielding states in which the controller can be reasonably expected to generate a meaningful response. Our defense strategy allows us to treat the controller and environment as black-boxes with unknown dynamics.
  arXiv  Detail & Related papers  (2020-06-11T22:29:07Z)
• Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped [64.64924554743982]
  We present a framework for implementing central pattern generators with spiking neural networks to obtain closed loop robot control. We demonstrate the learning of predefined gait patterns, speed control and gait transition on a simulated model of a compliant quadrupedal robot.
  arXiv  Detail & Related papers  (2020-04-09T14:32:49Z)

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.