The growing deployment of Large Vision-Language Models (VLMs) raises safety concerns, as adversaries may exploit model vulnerabilities to induce harmful outputs, with targeted black-box adversarial attacks posing a particularly severe threat. However, existing methods primarily maximize encoder-level global similarity, which lacks the granularity for stealthy and practical fine-grained attacks, where only specific target should be altered (e.g., modifying a car while preserving its background). Moreover, they largely neglect the projector, a key semantic bridge in VLMs for multimodal alignment. To address these limitations, we propose a novel black-box targeted attack framework that leverages the projector. Specifically, we utilize the widely adopted Querying Transformer (Q-Former) which transforms global image embeddings into fine-grained query outputs, to enhance attack effectiveness and granularity. For global targeted attack scenarios, we propose the Intermediate Projector Guided Attack (IPGA), which aligns the fine-grained query outputs from Q-Former with the target to enhance attack strength and exploits the intermediate pretrained Q-Former that is not fine-tuned for any specific Large Language Model (LLM) to improve transferability. For fine-grained attack scenarios, we augment IPGA with the Residual Query Alignment (RQA), which preserves unrelated content by constraining non-target query outputs, enhancing attack granularity. Extensive experiments demonstrate that IPGA significantly outperforms baselines in global targeted attacks, and IPGA with RQA (IPGA-R) attains superior success rates and content preservation over baselines in fine-grained attacks. Our method also transfers effectively to commercial VLMs such as Google Gemini and OpenAI GPT.

Adversarial examples generated on a surrogate deep neural network (DNN) can often successfully fool other black-box DNN models. This cross-model transferability poses serious security threats to DNNs in practical applications. Input transformation techniques are widely used to enhance adversarial transferability by increasing the diversity of input images. However, existing methods primarily rely on local operations with limited degrees of freedom (DOF), such as block-wise shuffling and resizing, overlooking global perspective transformations that naturally arise from viewpoint changes. In this work, we propose a Perspective-Invariant Attack (PIA), which introduces a multi-DOF vertex sampling strategy that systematically covers the perspective transformation hierarchy from 2-DOF translation to 8-DOF projective mapping. By generating geometrically diverse input variations, PIA effectively reduces overfitting of adversarial perturbations to the surrogate model, thereby improving adversarial transferability. We further propose PIA-Mix, a generic extension that maintains a complementary transformation pool and efficiently combines our perspective transformation with auxiliary methods for improved transferability. Extensive experiments involving various DNN architectures, advanced defense mechanisms, and multimodal large language models (LLMs) demonstrate that PIA and PIA-Mix outperform state-of-the-art transfer-based attacks.

Deep neural networks (DNNs) exhibit vulnerability to adversarial examples that can transfer across different DNN models. A particularly challenging problem is developing transferable targeted attacks that can mislead DNN models into predicting specific target classes. While various methods have been proposed to enhance attack transferability, they often incur substantial computational costs while yielding limited improvements. Recent clean feature mixup methods use random clean features to perturb the feature space but lack optimization for disrupting adversarial examples, overlooking the advantages of attack-specific perturbations. In this paper, we propose Feature Tuning Mixup (FTM), a novel method that enhances targeted attack transferability by combining both random and optimized noises in the feature space. FTM introduces learnable feature perturbations and employs an efficient stochastic update strategy for optimization. These learnable perturbations facilitate the generation of more robust adversarial examples with improved transferability. We further demonstrate that attack performance can be enhanced through an ensemble of multiple FTM-perturbed surrogate models. Extensive experiments on the ImageNet-compatible dataset across various DNN models demonstrate that our method achieves significant improvements over state-of-the-art methods while maintaining low computational cost.1

Recent works have attacked person detectors using adversarial patches or static-3D-model-based texture modifications. However, these methods suffer from low attack success rates when faced with significant human movements. The primary challenge stems from the highly non-rigid nature of the human body and clothing. Current attacks fail to model these 3D non-rigid deformations caused by varied actions. Fortunately, recent research has shown significant progress in using NeRF for dynamic human modeling. In this paper, we introduce \texttt{UV-Attack}, a novel physical adversarial attack achieving high attack success rates in scenarios involving extensive and unseen actions. We address the challenges above by leveraging dynamic-NeRF-based UV mapping. Our method can generate human images across diverse actions and viewpoints and even create novel unseen actions by sampling from the SMPL parameter space. While dynamic NeRF models are capable of modeling human bodies, modifying their clothing textures is challenging due to the texture being embedded within neural network parameters. To overcome this, \texttt{UV-Attack} generates UV maps instead of RGB images and modifies the texture stacks. This approach enables real-time texture edits and makes attacks more practical. Finally, we propose a novel Expectation over Pose Transformation loss (EoPT) to improve the evasion success rate on unseen poses and views. Our experiments show that \texttt{UV-Attack} achieves a 92.7\% attack success rate against the FastRCNN model across varied poses in dynamic video settings, significantly outperforming the state-of-the-art AdvCaT attack, which only had a 28.5\% ASR. Moreover, we achieve 49.5\% ASR on the latest YOLOv8 detector in black-box settings. The code is available at https://github.com/PolyLiYJ/UV-Attack

Adversarial attacks can mislead deep neural networks (DNNs) by adding imperceptible perturbations to benign examples. The attack transferability enables adversarial examples to attack blackbox DNNs with unknown architectures or parameters, which poses threats to many realworld applications. We find that existing transferable attacks do not distinguish between style and content features during optimization, limiting their attack transferability. To improve attack transferability, we propose a novel attack method called style-less perturbation (StyLess). Specifically, instead of using a vanilla network as the surrogate model, we advocate using stylized networks, which encode different style features by perturbing an adaptive instance normalization. Our method can prevent adversarial examples from using non-robust style features and help generate transferable perturbations. Comprehensive experiments show that our method can significantly improve the transferability of adversarial examples. Furthermore, our approach is generic and can outperform state-of-the-art transferable attacks when combined with other attack techniques.11Our code is available at https://github.com/uhiu/StyLess