Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

• URL: http://arxiv.org/abs/2506.07214v1
• Date: Sun, 08 Jun 2025 16:40:40 GMT
• Title: Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
• Authors: Zhiyuan Zhong, Zhen Sun, Yepang Liu, Xinlei He, Guanhong Tao,
• Abstract summary: BadSem is a data poisoning attack that injects backdoors by deliberately misaligning image-text pairs during training.<n>Our experiments show that BadSem achieves over 98% average ASR, generalizes well to out-of-distribution datasets, and can transfer across poisoning modalities.<n>Our findings highlight the urgent need to address semantic vulnerabilities in Vision Language Models for their safer deployment.
• Score: 32.24294112337828
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality triggers, leaving the crucial cross-modal fusion nature of VLMs largely unexplored. Unlike prior work, we identify a novel attack surface that leverages cross-modal semantic mismatches as implicit triggers. Based on this insight, we propose BadSem (Backdoor Attack with Semantic Manipulation), a data poisoning attack that injects stealthy backdoors by deliberately misaligning image-text pairs during training. To perform the attack, we construct SIMBad, a dataset tailored for semantic manipulation involving color and object attributes. Extensive experiments across four widely used VLMs show that BadSem achieves over 98% average ASR, generalizes well to out-of-distribution datasets, and can transfer across poisoning modalities. Our detailed analysis using attention visualization shows that backdoored models focus on semantically sensitive regions under mismatched conditions while maintaining normal behavior on clean inputs. To mitigate the attack, we try two defense strategies based on system prompt and supervised fine-tuning but find that both of them fail to mitigate the semantic backdoor. Our findings highlight the urgent need to address semantic vulnerabilities in VLMs for their safer deployment.

Related papers

• Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments [61.808686396077036]
  We present GHOST, the first clean-label backdoor attack specifically designed for mobile agents built upon vision-language models (VLMs)<n>Our method manipulates only the visual inputs of a portion of the training samples without altering their corresponding labels or instructions.<n>We evaluate our method across six real-world Android apps and three VLM architectures adapted for mobile use.
  arXiv  Detail & Related papers  (2025-06-16T08:09:32Z)
• SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs [57.880467106470775]
  Attackers can inject imperceptible perturbations into the training data, causing the model to generate malicious, attacker-controlled captions.<n>We propose Semantic Reward Defense (SRD), a reinforcement learning framework that mitigates backdoor behavior without prior knowledge of triggers.<n>SRD uses a Deep Q-Network to learn policies for applying discrete perturbations to sensitive image regions, aiming to disrupt the activation of malicious pathways.
  arXiv  Detail & Related papers  (2025-06-05T08:22:24Z)
• Propaganda via AI? A Study on Semantic Backdoors in Large Language Models [7.282200564983221]
  We show that semantic backdoors can be implanted with only a small poisoned corpus.<n>We introduce a black-box detection framework, RAVEN, which combines semantic entropy with cross-model consistency analysis.<n> Empirical evaluations uncover previously undetected semantic backdoors.
  arXiv  Detail & Related papers  (2025-04-15T16:43:15Z)
• Towards Invisible Backdoor Attack on Text-to-Image Diffusion Model [70.03122709795122]
  Backdoor attacks targeting text-to-image diffusion models have advanced rapidly.<n>Current backdoor samples often exhibit two key abnormalities compared to benign samples.<n>We propose a novel Invisible Backdoor Attack (IBA) to enhance the stealthiness of backdoor samples.
  arXiv  Detail & Related papers  (2025-03-22T10:41:46Z)
• Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift [104.76588209308666]
  This paper explores backdoor attacks in LVLM instruction tuning across mismatched training and testing domains.<n>We introduce a new evaluation dimension, backdoor domain generalization, to assess attack robustness.<n>We propose a multimodal attribution backdoor attack (MABA) that injects domain-agnostic triggers into critical areas.
  arXiv  Detail & Related papers  (2024-06-27T02:31:03Z)
• 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)
• Backdoor Attack with Sparse and Invisible Trigger [57.41876708712008]
  Deep neural networks (DNNs) are vulnerable to backdoor attacks. backdoor attack is an emerging yet threatening training-phase threat. We propose a sparse and invisible backdoor attack (SIBA)
  arXiv  Detail & Related papers  (2023-05-11T10:05:57Z)
• 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)
• Hidden Backdoor Attack against Semantic Segmentation Models [60.0327238844584]
  The emphbackdoor attack intends to embed hidden backdoors in deep neural networks (DNNs) by poisoning training data. We propose a novel attack paradigm, the emphfine-grained attack, where we treat the target label from the object-level instead of the image-level. Experiments show that the proposed methods can successfully attack semantic segmentation models by poisoning only a small proportion of training data.
  arXiv  Detail & Related papers  (2021-03-06T05:50:29Z)

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.