Triggering hallucinations in model-based MRI reconstruction via adversarial perturbations

• URL: http://arxiv.org/abs/2602.18536v1
• Date: Fri, 20 Feb 2026 11:55:22 GMT
• Title: Triggering hallucinations in model-based MRI reconstruction via adversarial perturbations
• Authors: Suna Buğday, Yvan Saeys, Jonathan Peck,
• Abstract summary: hallucinations may endanger patient health as they can lead to incorrect diagnoses.<n>In this work, we aim to quantify the extent to which state-of-the-art generative models suffer from hallucinations in the context of magnetic resonance image reconstruction.<n>We perform this evaluation on the brain and knee images from the fastMRI data set using UNet and end-to-end VarNet architectures.
• Score: 3.325046116674658
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative models are increasingly used to improve the quality of medical imaging, such as reconstruction of magnetic resonance images and computed tomography. However, it is well-known that such models are susceptible to hallucinations: they may insert features into the reconstructed image which are not actually present in the original image. In a medical setting, such hallucinations may endanger patient health as they can lead to incorrect diagnoses. In this work, we aim to quantify the extent to which state-of-the-art generative models suffer from hallucinations in the context of magnetic resonance image reconstruction. Specifically, we craft adversarial perturbations resembling random noise for the unprocessed input images which induce hallucinations when reconstructed using a generative model. We perform this evaluation on the brain and knee images from the fastMRI data set using UNet and end-to-end VarNet architectures to reconstruct the images. Our results show that these models are highly susceptible to small perturbations and can be easily coaxed into producing hallucinations. This fragility may partially explain why hallucinations occur in the first place and suggests that a carefully constructed adversarial training routine may reduce their prevalence. Moreover, these hallucinations cannot be reliably detected using traditional image quality metrics. Novel approaches will therefore need to be developed to detect when hallucinations have occurred.

Related papers

• HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restoration [8.702496582146042]
  HalluGen is a diffusion-based framework that synthesizes realistic hallucinations with controllable type, location, and severity.<n>We construct the first large-scale hallucination dataset comprising 4,350 annotated images.<n>HalluGen and its open dataset establish the first scalable foundation for evaluating hallucinations in safety-critical image restoration.
  arXiv  Detail & Related papers  (2025-12-03T01:20:00Z)
• Counting Hallucinations in Diffusion Models [34.45858211220468]
  Diffusion probabilistic models (DPMs) have demonstrated remarkable progress in generative tasks, such as image and video synthesis.<n>They often produce hallucinated samples (hallucinations) that conflict with real-world knowledge.<n>Despite their prevalence, the lack of feasible methodologies for systematically quantifying such hallucinations hinders progress.
  arXiv  Detail & Related papers  (2025-10-15T01:48:04Z)
• GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs [61.829473661517675]
  We introduce GHOST, a method designed to stress-test MLLMs by actively generating images that induce hallucination.<n>GHOST is fully automatic and requires no human supervision or prior knowledge.<n>We evaluate our method across a range of models, including reasoning models like GLM-4.1V-Thinking, and achieve a hallucination success rate exceeding 28%, compared to around 1% in prior data-driven discovery methods.
  arXiv  Detail & Related papers  (2025-09-29T17:59:23Z)
• Trustworthy Medical Imaging with Large Language Models: A Study of Hallucinations Across Modalities [3.1406146587437904]
  Large Language Models (LLMs) are increasingly applied to medical imaging tasks.<n>These models often produce hallucinations, which are confident but incorrect outputs that can mislead clinical decisions.<n>This study examines hallucinations in two directions: image to text, where LLMs generate reports from X-ray, CT, or MRI scans, and text to image, where models create medical images from clinical prompts.
  arXiv  Detail & Related papers  (2025-08-09T16:03:46Z)
• Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling [78.78822033285938]
  Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations.<n>In this work, we introduce REVERSE, a unified framework that integrates hallucination-aware training with on-the-fly self-verification.
  arXiv  Detail & Related papers  (2025-04-17T17:59:22Z)
• Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations [82.42811602081692]
  This paper introduces a subsequence association framework to systematically trace and understand hallucinations.<n>Key insight is hallucinations that arise when dominant hallucinatory associations outweigh faithful ones.<n>We propose a tracing algorithm that identifies causal subsequences by analyzing hallucination probabilities across randomized input contexts.
  arXiv  Detail & Related papers  (2025-04-17T06:34:45Z)
• Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer [51.7407540261676]
  We investigate a distinct type of hallucination, where a model can consistently answer a question correctly, but a seemingly trivial perturbation causes it to produce a hallucinated response with high certainty.<n>This phenomenon is particularly concerning in high-stakes domains such as medicine or law, where model certainty is often used as a proxy for reliability.<n>We show that CHOKE examples are consistent across prompts, occur in different models and datasets, and are fundamentally distinct from other hallucinations.
  arXiv  Detail & Related papers  (2025-02-18T15:46:31Z)
• Hallucinations in Neural Automatic Speech Recognition: Identifying Errors and Hallucinatory Models [11.492702369437785]
  Hallucinations are semantically unrelated to the source utterance, yet still fluent and coherent. We show that commonly used metrics, such as word error rates, cannot differentiate between hallucinatory and non-hallucinatory models. We devise a framework for identifying hallucinations by analysing their semantic connection with the ground truth and their fluency.
  arXiv  Detail & Related papers  (2024-01-03T06:56:56Z)
• Volumetric Reconstruction Resolves Off-Resonance Artifacts in Static and Dynamic PROPELLER MRI [76.60362295758596]
  Off-resonance artifacts in magnetic resonance imaging (MRI) are visual distortions that occur when the actual resonant frequencies of spins within the imaging volume differ from the expected frequencies used to encode spatial information. We propose to resolve these artifacts by lifting the 2D MRI reconstruction problem to 3D, introducing an additional "spectral" dimension to model this off-resonance.
  arXiv  Detail & Related papers  (2023-11-22T05:44:51Z)
• Reducing Hallucinations in Neural Machine Translation with Feature Attribution [54.46113444757899]
  We present a case study focusing on model understanding and regularisation to reduce hallucinations in NMT. We first use feature attribution methods to study the behaviour of an NMT model that produces hallucinations. We then leverage these methods to propose a novel loss function that substantially helps reduce hallucinations and does not require retraining the model from scratch.
  arXiv  Detail & Related papers  (2022-11-17T20:33:56Z)

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.