cs.CVOct 31, 2026

Context-Shielded Backdoor Attack against Large Vision-Language Models

Authors: Zhifang Zhang, Qiang Huang, Chenpeng Wang, Weitong Chen, Olaf Maennel, Wei Emma Zhang, Lei Feng, Lei Zhang, 

Organizations: The University of Queensland · Fudan University · YiXin-AILab · Adelaide University · 

Abstract

Large vision-language models (LVLMs) routinely use inference-time visual-token compression to prune hundreds of patch tokens down to a compact budget. Existing LVLM backdoors fire whenever a triggered image appears, whereas prior deployment-triggered attacks activate only when model weights are quantized or pruned. However, conventional LVLM backdoors exhibit nearly 100% attack success rate (ASR) under full-token inference, immediately exposing compromised checkpoints during pre-deployment auditing. We reveal context stripping: surrounding clean visual tokens suppress an embedded trigger at full length, whereas token pruning strips this context away and activates the backdoor. Motivated by this finding, we propose StripWake, a projector-only backdoor that remains dormant under full-token auditing yet activates across unseen compressors. Specifically, StripWake pairs clean-supervised full-token views with target-supervised randomized compressed views, and aligns early visual attention with a frozen benign teacher to preserve clean utility. On LLaVA-1.5-7B across nine unseen compressors, StripWake stays dormant at 0.4% full-token ASR yet achieves 94.0%-99.7% compressed ASR across five primary compressors without CIDEr loss.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 29, 2025

TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models

Large vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable to backdoor attacks. Existing backdoor attacks on LVLMs aim to force the victim model to generate a predefined target pattern, which is either inserted into or replaces the original content. We find that these fixed-pattern attacks are relatively easy to detect, because the attacked LVLM tends to memorize such frequent patterns in the training dataset, thereby exhibiting overconfidence on these targets given poisoned inputs. To address these limitations, we introduce TokenSwap, a more evasive and stealthy backdoor attack that focuses on the compositional understanding capabilities of LVLMs. Instead of enforcing a fixed targeted content, TokenSwap subtly disrupts the understanding of object relationships in text. Specifically, it causes the backdoored model to generate outputs that mention the correct objects in the image but misrepresent their relationships (i.e., bags-of-words behavior). During training, TokenSwap injects a visual trigger into selected samples and simultaneously swaps the grammatical roles of key tokens in the corresponding textual answers. However, the poisoned samples exhibit only subtle differences from the original ones, making it challenging for the model to learn the backdoor behavior. To address this, TokenSwap employs an adaptive token-weighted loss that explicitly emphasizes the learning of swapped tokens, such that the visual triggers and bags-of-words behavior are associated. Extensive experiments demonstrate that TokenSwap achieves high attack success rates while maintaining superior evasiveness and stealthiness across multiple benchmarks and various LVLM architectures.
Mar 13, 2026

Test-Time Attention Purification for Backdoored Large Vision Language Models

Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be maliciously activated at test time. Existing defenses typically rely on retraining backdoored parameters (e.g., adapters or LoRA modules) with clean data, which is computationally expensive and often degrades model performance. In this work, we provide a new mechanistic understanding of backdoor behaviors in LVLMs: the trigger does not influence prediction through low-level visual patterns, but through abnormal cross-modal attention redistribution, where trigger-bearing visual tokens steal attention away from the textual context - a phenomenon we term attention stealing. Motivated by this, we propose CleanSight, a training-free, plug-and-play defense that operates purely at test time. CleanSight (i) detects poisoned inputs based on the relative visual-text attention ratio in selected cross-modal fusion layers, and (ii) purifies the input by selectively pruning the suspicious high-attention visual tokens to neutralize the backdoor activation. Extensive experiments show that CleanSight significantly outperforms existing pixel-based purification defenses across diverse datasets and backdoor attack types, while preserving the model's utility on both clean and poisoned samples.
Sep 30, 2026

Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models

Visual-token compression improves the efficiency of large vision-language models, but can expose failures that full-token evaluation misses. We study adversarial images that preserve full-token correctness yet induce errors after compression, even when both inference paths succeed on the clean image. Creating such failures is challenging because perturbing token importance can also damage the visual content needed for full-token inference. We propose Feature-Aware Token Attack (FATA), which couples attention suppression with cosine-based feature preservation on a fixed set of salient clean-image tokens. In the primary LLaVA-1.5-7B setting, FATA uses only vision-encoder gradients, without access to the deployed compressor, token budget, or downstream task. Across four visually dependent task subsets and four compressors under a controlled reconstruction protocol, FATA achieves SR = 96.3% full-token accuracy retention and CBR = 22.1% conditional blinding, compared with 89.8% and 15.7% for CAA. Ablations support the role of both objectives in balancing compressed-path failure against full-token preservation. FATA also has the lowest measured detection rate among four attacks across three evaluated detectors at a 5% false-positive rate. These findings motivate assessing adversarial robustness jointly across full-token and compressed inference.