Chengyin Hu

Chengyin Hu, Yilong Wang, Kalibinuer Tiliwalidi et al.

Most existing deep neural networks (DNNs) are easily disturbed by slight noise. However, there are few researches on physical attacks by deploying lighting equipment. The light-based physical attacks has excellent covertness, which brings great security risks to many vision-based applications (such as self-driving). Therefore, we propose a light-based physical attack, called adversarial laser spot (AdvLS), which optimizes the physical parameters of laser spots through genetic algorithm to perform physical attacks. It realizes robust and covert physical attack by using low-cost laser equipment. As far as we know, AdvLS is the first light-based physical attack that perform physical attacks in the daytime. A large number of experiments in the digital and physical environments show that AdvLS has excellent robustness and covertness. In addition, through in-depth analysis of the experimental data, we find that the adversarial perturbations generated by AdvLS have superior adversarial attack migration. The experimental results show that AdvLS impose serious interference to advanced DNNs, we call for the attention of the proposed AdvLS. The code of AdvLS is available at: https://github.com/ChengYinHu/AdvLS

Chengyin Hu, Weiwen Shi, Tingsong Jiang et al.

Infrared imaging systems have a vast array of potential applications in pedestrian detection and autonomous driving, and their safety performance is of great concern. However, few studies have explored the safety of infrared imaging systems in real-world settings. Previous research has used physical perturbations such as small bulbs and thermal "QR codes" to attack infrared imaging detectors, but such methods are highly visible and lack stealthiness. Other researchers have used hot and cold blocks to deceive infrared imaging detectors, but this method is limited in its ability to execute attacks from various angles. To address these shortcomings, we propose a novel physical attack called adversarial infrared blocks (AdvIB). By optimizing the physical parameters of the adversarial infrared blocks, this method can execute a stealthy black-box attack on thermal imaging system from various angles. We evaluate the proposed method based on its effectiveness, stealthiness, and robustness. Our physical tests show that the proposed method achieves a success rate of over 80% under most distance and angle conditions, validating its effectiveness. For stealthiness, our method involves attaching the adversarial infrared block to the inside of clothing, enhancing its stealthiness. Additionally, we test the proposed method on advanced detectors, and experimental results demonstrate an average attack success rate of 51.2%, proving its robustness. Overall, our proposed AdvIB method offers a promising avenue for conducting stealthy, effective and robust black-box attacks on thermal imaging system, with potential implications for real-world safety and security applications.

Chengyin Hu, Weiwen Shi

It is well known that the performance of deep neural networks (DNNs) is susceptible to subtle interference. So far, camera-based physical adversarial attacks haven't gotten much attention, but it is the vacancy of physical attack. In this paper, we propose a simple and efficient camera-based physical attack called Adversarial Color Film (AdvCF), which manipulates the physical parameters of color film to perform attacks. Carefully designed experiments show the effectiveness of the proposed method in both digital and physical environments. In addition, experimental results show that the adversarial samples generated by AdvCF have excellent performance in attack transferability, which enables AdvCF effective black-box attacks. At the same time, we give the guidance of defense against AdvCF by means of adversarial training. Finally, we look into AdvCF's threat to future vision-based systems and propose some promising mentality for camera-based physical attacks.

Xiang Chen, Yuxian Dong, Chao Li et al.

Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, but their adversarial robustness in visible-infrared (VIS-IR) scenarios remains underexplored. This gap is critical because VIS-IR sensing is widely used in real-world perception systems to support reliable understanding under challenging imaging conditions. To address this cross-modal threat setting, we propose CFGPatch, a curved-edge fractal geometric adversarial patch framework for attacking VIS-IR VLMs. CFGPatch builds on triangular fractal geometry and replaces rigid straight-edged primitives with Bezier-curved elements, preserving multi-scale fractal self-similarity while introducing smoother contours, richer directional variation, and more flexible shape deformation. In addition, we design a modality-specific Fraser-spiral rendering mechanism to inject fine-grained texture distortions and misleading perceptual cues into visible and infrared images. By coupling global curved-fractal geometry with local spiral-based appearance interference, CFGPatch disrupts both shape perception and texture interpretation. We further adopt expectation over transformation (EOT) to improve robustness against common image-level transformations. Extensive experiments show that CFGPatch effectively fools VIS-IR VLMs and consistently outperforms standard patch baselines in attack effectiveness and robustness. Moreover, adversarial samples optimized for zero-shot classification transfer well to image captioning and visual question answering, demonstrating strong cross-task transferability and generalizability across downstream tasks.

Chunlei Meng, Jiabin Luo, Pengbin Feng et al.

Multimodal Sentiment Analysis (MSA) requires integrating language, acoustic, and visual signals without sacrificing modality-specific sentiment evidence. Existing methods mainly improve either shared-private decomposition or cross-modal interaction. Although effective, both ultimately depend on how shared and modality-specific evidence is organized before prediction. We observe that, under standard shared-private pipelines, modality heterogeneity often induces a branch-imbalance process: dominant shared patterns accumulate in the shared branch, yielding redundant and modality-biased evidence, while repeated interaction and rigid alignment gradually leak shared information into modality-specific channels and weaken discriminative private representations. As a result, the complementarity between shared and private representations is reduced, limiting robust sentiment reasoning. To address this issue, we propose the Dual-Branch Rebalancing Framework (DBR) on top of a standard multimodal decoupling stage. In the shared branch, a Temporal-Structural Factorization (TSF) module disentangles temporal evolution from structural dependencies and adaptively integrates them to reduce shared redundancy. In the private branch, an Anchor-Guided Private Routing (AGPR) module preserves discriminative modality-specific patterns while allowing controlled cross-modal borrowing. A Bidirectional Rebalancing Fusion (BRF) module then reunifies the two regularized branches in a context-aware manner for final prediction. Extensive experiments on CMU-MOSI, CMU-MOSEI, and MIntRec demonstrate that DBR consistently outperforms the compared baselines. Further analyses show that these improvements come from coordinated mitigation of branch imbalance.

Chengyin Hu, Weiwen Shi, Wen Li

In the physical world, deep neural networks (DNNs) are impacted by light and shadow, which can have a significant effect on their performance. While stickers have traditionally been used as perturbations in most physical attacks, their perturbations can often be easily detected. To address this, some studies have explored the use of light-based perturbations, such as lasers or projectors, to generate more subtle perturbations, which are artificial rather than natural. In this study, we introduce a novel light-based attack called the adversarial neon beam (AdvNB), which utilizes common neon beams to create a natural black-box physical attack. Our approach is evaluated on three key criteria: effectiveness, stealthiness, and robustness. Quantitative results obtained in simulated environments demonstrate the effectiveness of the proposed method, and in physical scenarios, we achieve an attack success rate of 81.82%, surpassing the baseline. By using common neon beams as perturbations, we enhance the stealthiness of the proposed attack, enabling physical samples to appear more natural. Moreover, we validate the robustness of our approach by successfully attacking advanced DNNs with a success rate of over 75% in all cases. We also discuss defense strategies against the AdvNB attack and put forward other light-based physical attacks.

Chengyin Hu, Weiwen Shi

Deep neural networks (DNNs) have demonstrated exceptional success across various tasks, underscoring the need to evaluate the robustness of advanced DNNs. However, traditional methods using stickers as physical perturbations to deceive classifiers present challenges in achieving stealthiness and suffer from printing loss. Recent advancements in physical attacks have utilized light beams such as lasers and projectors to perform attacks, where the optical patterns generated are artificial rather than natural. In this study, we introduce a novel physical attack, adversarial catoptric light (AdvCL), where adversarial perturbations are generated using a common natural phenomenon, catoptric light, to achieve stealthy and naturalistic adversarial attacks against advanced DNNs in a black-box setting. We evaluate the proposed method in three aspects: effectiveness, stealthiness, and robustness. Quantitative results obtained in simulated environments demonstrate the effectiveness of the proposed method, and in physical scenarios, we achieve an attack success rate of 83.5%, surpassing the baseline. We use common catoptric light as a perturbation to enhance the stealthiness of the method and make physical samples appear more natural. Robustness is validated by successfully attacking advanced and robust DNNs with a success rate over 80% in all cases. Additionally, we discuss defense strategy against AdvCL and put forward some light-based physical attacks.

Chengyin Hu, Weiwen Shi

Although deep neural networks (DNNs) are known to be fragile, no one has studied the effects of zooming-in and zooming-out of images in the physical world on DNNs performance. In this paper, we demonstrate a novel physical adversarial attack technique called Adversarial Zoom Lens (AdvZL), which uses a zoom lens to zoom in and out of pictures of the physical world, fooling DNNs without changing the characteristics of the target object. The proposed method is so far the only adversarial attack technique that does not add physical adversarial perturbation attack DNNs. In a digital environment, we construct a data set based on AdvZL to verify the antagonism of equal-scale enlarged images to DNNs. In the physical environment, we manipulate the zoom lens to zoom in and out of the target object, and generate adversarial samples. The experimental results demonstrate the effectiveness of AdvZL in both digital and physical environments. We further analyze the antagonism of the proposed data set to the improved DNNs. On the other hand, we provide a guideline for defense against AdvZL by means of adversarial training. Finally, we look into the threat possibilities of the proposed approach to future autonomous driving and variant attack ideas similar to the proposed attack.

Chengyin Hu, Weiwen Shi

Deep neural networks (DNNs) have been widely used in computer vision tasks like image classification, object detection and segmentation. Whereas recent studies have shown their vulnerability to manual digital perturbations or distortion in the input images. The accuracy of the networks is remarkably influenced by the data distribution of their training dataset. Scaling the raw images creates out-of-distribution data, which makes it a possible adversarial attack to fool the networks. In this work, we propose a Scaling-distortion dataset ImageNet-CS by Scaling a subset of the ImageNet Challenge dataset by different multiples. The aim of our work is to study the impact of scaled images on the performance of advanced DNNs. We perform experiments on several state-of-the-art deep neural network architectures on the proposed ImageNet-CS, and the results show a significant positive correlation between scaling size and accuracy decline. Moreover, based on ResNet50 architecture, we demonstrate some tests on the performance of recent proposed robust training techniques and strategies like Augmix, Revisiting and Normalizer Free on our proposed ImageNet-CS. Experiment results have shown that these robust training techniques can improve networks' robustness to scaling transformation.

Yingying Zhao, Chengyin Hu, Qike Zhang et al.

Vision-Language Models (VLMs) have shown remarkable performance, yet their security remains insufficiently understood. Existing adversarial studies focus almost exclusively on the digital setting, leaving physical-world threats largely unexplored. As VLMs are increasingly deployed in real environments, this gap becomes critical, since adversarial perturbations must be physically realizable. Despite this practical relevance, physical attacks against VLMs have not been systematically studied. Such attacks may induce recognition failures and further disrupt multimodal reasoning, leading to severe semantic misinterpretation in downstream tasks. Therefore, investigating physical attacks on VLMs is essential for assessing their real-world security risks. To address this gap, we propose Multimodal Semantic Lighting Attacks (MSLA), the first physically deployable adversarial attack framework against VLMs. MSLA uses controllable adversarial lighting to disrupt multimodal semantic understanding in real scenes, attacking semantic alignment rather than only task-specific outputs. Consequently, it degrades zero-shot classification performance of mainstream CLIP variants while inducing severe semantic hallucinations in advanced VLMs such as LLaVA and BLIP across image captioning and visual question answering (VQA). Extensive experiments in both digital and physical domains demonstrate that MSLA is effective, transferable, and practically realizable. Our findings provide the first evidence that VLMs are highly vulnerable to physically deployable semantic attacks, exposing a previously overlooked robustness gap and underscoring the urgent need for physical-world robustness evaluation of VLMs.

Kalibinuer Tiliwalidi, Chengyin Hu, Weiwen Shi

While extensive research exists on physical adversarial attacks within the visible spectrum, studies on such techniques in the infrared spectrum are limited. Infrared object detectors are vital in modern technological applications but are susceptible to adversarial attacks, posing significant security threats. Previous studies using physical perturbations like light bulb arrays and aerogels for white-box attacks, or hot and cold patches for black-box attacks, have proven impractical or limited in multi-view support. To address these issues, we propose the Adversarial Infrared Grid (AdvGrid), which models perturbations in a grid format and uses a genetic algorithm for black-box optimization. These perturbations are cyclically applied to various parts of a pedestrian's clothing to facilitate multi-view black-box physical attacks on infrared pedestrian detectors. Extensive experiments validate AdvGrid's effectiveness, stealthiness, and robustness. The method achieves attack success rates of 80.00\% in digital environments and 91.86\% in physical environments, outperforming baseline methods. Additionally, the average attack success rate exceeds 50\% against mainstream detectors, demonstrating AdvGrid's robustness. Our analyses include ablation studies, transfer attacks, and adversarial defenses, confirming the method's superiority.

Chengyin Hu, Weiwen Shi, Ling Tian

Recent research has demonstrated that deep neural networks (DNNs) are vulnerable to adversarial perturbations. Therefore, it is imperative to evaluate the resilience of advanced DNNs to adversarial attacks. However, traditional methods that use stickers as physical perturbations to deceive classifiers face challenges in achieving stealthiness and are susceptible to printing loss. Recently, advancements in physical attacks have utilized light beams, such as lasers, to perform attacks, where the optical patterns generated are artificial rather than natural. In this work, we propose a black-box projector-based physical attack, referred to as adversarial color projection (AdvCP), which manipulates the physical parameters of color projection to perform an adversarial attack. We evaluate our approach on three crucial criteria: effectiveness, stealthiness, and robustness. In the digital environment, we achieve an attack success rate of 97.60% on a subset of ImageNet, while in the physical environment, we attain an attack success rate of 100% in the indoor test and 82.14% in the outdoor test. The adversarial samples generated by AdvCP are compared with baseline samples to demonstrate the stealthiness of our approach. When attacking advanced DNNs, experimental results show that our method can achieve more than 85% attack success rate in all cases, which verifies the robustness of AdvCP. Finally, we consider the potential threats posed by AdvCP to future vision-based systems and applications and suggest some ideas for light-based physical attacks.

Chengyin Hu, Jiaju Han, Xuemeng Sun et al.

Vision-language models (VLMs) rely on a shared visual-textual representation space to perform tasks such as zero-shot classification, image captioning, and visual question answering (VQA). While this shared space enables strong cross-task generalization, it may also introduce a common vulnerability: small visual perturbations can propagate through the shared embedding space and cause correlated semantic failures across tasks. This risk is particularly important in interactive and decision-support settings, yet it remains unclear whether VLMs are robust to highly constrained, sparse, and geometrically fixed perturbations. To address this question, we propose X-shaped Sparse Pixel Attack (XSPA), an imperceptible structured attack that restricts perturbations to two intersecting diagonal lines. Compared with dense perturbations or flexible localized patches, XSPA operates under a much stricter attack budget and thus provides a more stringent test of VLM robustness. Within this sparse support, XSPA jointly optimizes a classification objective, cross-task semantic guidance, and regularization on perturbation magnitude and along-line smoothness, inducing transferable misclassification as well as semantic drift in captioning and VQA while preserving visual subtlety. Under the default setting, XSPA modifies only about 1.76% of image pixels. Experiments on the COCO dataset show that XSPA consistently degrades performance across all three tasks. Zero-shot accuracy drops by 52.33 points on OpenAI CLIP ViT-L/14 and 67.00 points on OpenCLIP ViT-B/16, while GPT-4-evaluated caption consistency decreases by up to 58.60 points and VQA correctness by up to 44.38 points. These results suggest that even highly sparse and visually subtle perturbations with fixed geometric priors can substantially disrupt cross-task semantics in VLMs, revealing a notable robustness gap in current multimodal systems.

Chengyin Hu, Xuemeng Sun, Jiajun Han et al.

Visual-Language Models (VLMs) have demonstrated exceptional cross-modal understanding across various tasks, including zero-shot classification, image captioning, and visual question answering. However, their robustness to physically plausible non-rigid deformations-such as wrinkles on flexible surfaces-remains poorly understood. In this work, we propose a parametric structural perturbation method inspired by the mechanics of three-dimensional fabric wrinkles. Specifically, our method generates photorealistic non-rigid perturbations by constructing multi-scale wrinkle fields and integrating displacement field distortion with surface-consistent appearance variations. To achieve an optimal balance between visual naturalness and adversarial effectiveness, we design a hierarchical fitness function in a low-dimensional parameter space and employ an optimization-based search strategy. We evaluate our approach using a two-stage framework: perturbations are first optimized on a zero-shot classification proxy task and subsequently assessed for transferability on generative tasks. Experimental results demonstrate that our method significantly degrades the performance of various state-of-the-art VLMs, consistently outperforming baselines in both image captioning and visual question-answering tasks.

Chengyin Hu, Weiwen Shi

Deep neural networks (DNNs) have have shown state-of-the-art performance for computer vision applications like image classification, segmentation and object detection. Whereas recent advances have shown their vulnerability to manual digital perturbations in the input data, namely adversarial attacks. The accuracy of the networks is significantly affected by the data distribution of their training dataset. Distortions or perturbations on color space of input images generates out-of-distribution data, which make networks more likely to misclassify them. In this work, we propose a color-variation dataset by distorting their RGB color on a subset of the ImageNet with 27 different combinations. The aim of our work is to study the impact of color variation on the performance of DNNs. We perform experiments on several state-of-the-art DNN architectures on the proposed dataset, and the result shows a significant correlation between color variation and loss of accuracy. Furthermore, based on the ResNet50 architecture, we demonstrate some experiments of the performance of recently proposed robust training techniques and strategies, such as Augmix, revisit, and free normalizer, on our proposed dataset. Experimental results indicate that these robust training techniques can improve the robustness of deep networks to color variation.

Xiang Chen, Fangfang Yang, Chunlei Meng et al.

Medical vision--language models (MVLMs) are increasingly used as perceptual backbones in radiology pipelines and as the visual front end of multimodal assistants, yet their reliability under real clinical workflows remains underexplored. Prior robustness evaluations often assume clean, curated inputs or study isolated corruptions, overlooking routine acquisition, reconstruction, display, and delivery operations that preserve clinical readability while shifting image statistics. To address this gap, we propose CoDA, a chain-of-distribution framework that constructs clinically plausible pipeline shifts by composing acquisition-like shading, reconstruction and display remapping, and delivery and export degradations. Under masked structural-similarity constraints, CoDA jointly optimizes stage compositions and parameters to induce failures while preserving visual plausibility. Across brain MRI, chest X-ray, and abdominal CT, CoDA substantially degrades the zero-shot performance of CLIP-style MVLMs, with chained compositions consistently more damaging than any single stage. We also evaluate multimodal large language models (MLLMs) as technical-authenticity auditors of imaging realism and quality rather than pathology. Proprietary multimodal models show degraded auditing reliability and persistent high-confidence errors on CoDA-shifted samples, while the medical-specific MLLMs we test exhibit clear deficiencies in medical image quality auditing. Finally, we introduce a post-hoc repair strategy based on teacher-guided token-space adaptation with patch-level alignment, which improves accuracy on archived CoDA outputs. Overall, our findings characterize a clinically grounded threat surface for MVLM deployment and show that lightweight alignment improves robustness in deployment.

Chengyin Hu, Yikun Guo, Yuxian Dong et al.

Although infrared pedestrian detectors have been widely deployed in visual perception tasks, their vulnerability to physical adversarial attacks is becoming increasingly apparent. Existing physical attack methods predominantly rely on instance-specific online optimization and rigid pattern design, leading to high deployment costs and insufficient physical robustness. To address these limitations, this work proposes the Universal Physical Patch Attack (UPPA), the first universal physical attack method in the infrared domain. This method employs geometrically constrained parameterized Bezier blocks to model perturbations and utilizes the Particle Swarm Optimization (PSO) algorithm to perform unified optimization across the global data distribution, thus maintaining topological stability under dynamic deformations. In the physical deployment phase, we materialize the optimized digital perturbations into physical cold patches, achieving a continuous and smooth low-temperature distribution that naturally aligns with the thermal radiation characteristics of infrared imaging. Extensive experiments demonstrate that UPPA achieves an outstanding physical attack success rate without any online computational overhead, while also exhibiting strong cross-domain generalization and reliable black-box transferability.

Jiaju Han, Chao Li, Chengyin Hu et al.

Multimodal RAG systems increasingly rely on vision-language retrievers to ground visual queries in external textual evidence. Existing adversarial studies on RAG mainly manipulate the retrieval corpus or memory, while attacks on vision-language and remote sensing models typically target end-task predictions. Input-space threats to the evidence retrieval stage of remote sensing multimodal RAG remain underexplored. To address this gap, we introduce CloudWeb, an atmospheric retrieval hijacking attack that modifies only the input image while keeping the retriever, generator, and knowledge base fixed at deployment. CloudWeb overlays parameterized cloud- and haze-like patterns on remote sensing images and optimizes them with a retrieval-oriented objective that pulls adversarial image embeddings toward target atmospheric evidence, suppresses source-scene evidence, enforces rank separation, and regularizes naturalness and coverage. To the best of our knowledge, this is the first study of retrieval-stage atmospheric evidence hijacking in remote sensing multimodal RAG. We evaluate CloudWeb on a seven-dataset remote sensing RAG benchmark with five CLIP-style retrievers, including GeoRSCLIP, RemoteCLIP, OpenAI CLIP, and OpenCLIP, together with downstream vision-language generators. Across retrievers, CloudWeb consistently outperforms clean retrieval, handcrafted atmospheric baselines, random cloud perturbations, and fixed variants in injecting weather-related evidence into top-ranked results. On GeoRSCLIP ViT-B/32, Weather@5 increases from 0.71\% to 43.29\%. Downstream generation further shows measurable weather hallucination and semantic shift, indicating that retrieval-stage hijacking can propagate to the final RAG response. These findings reveal a practical failure mode: natural-looking atmospheric changes can compromise evidence retrieval before generation begins.

Chengyin Hu, Weiwen Shi

Deep neural network security is a persistent concern, with considerable research on visible light physical attacks but limited exploration in the infrared domain. Existing approaches, like white-box infrared attacks using bulb boards and QR suits, lack realism and stealthiness. Meanwhile, black-box methods with cold and hot patches often struggle to ensure robustness. To bridge these gaps, we propose Adversarial Infrared Curves (AdvIC). Using Particle Swarm Optimization, we optimize two Bezier curves and employ cold patches in the physical realm to introduce perturbations, creating infrared curve patterns for physical sample generation. Our extensive experiments confirm AdvIC's effectiveness, achieving 94.8\% and 67.2\% attack success rates for digital and physical attacks, respectively. Stealthiness is demonstrated through a comparative analysis, and robustness assessments reveal AdvIC's superiority over baseline methods. When deployed against diverse advanced detectors, AdvIC achieves an average attack success rate of 76.8\%, emphasizing its robust nature. we explore adversarial defense strategies against AdvIC and examine its impact under various defense mechanisms. Given AdvIC's substantial security implications for real-world vision-based applications, urgent attention and mitigation efforts are warranted.

Chengyin Hu, Weiwen Shi

Currently, many studies have addressed security concerns related to visible and infrared detectors independently. In practical scenarios, utilizing cross-modal detectors for tasks proves more reliable than relying on single-modal detectors. Despite this, there is a lack of comprehensive security evaluations for cross-modal detectors. While existing research has explored the feasibility of attacks against cross-modal detectors, the implementation of a robust attack remains unaddressed. This work introduces the Two-stage Optimized Unified Adversarial Patch (TOUAP) designed for performing attacks against visible-infrared cross-modal detectors in real-world, black-box settings. The TOUAP employs a two-stage optimization process: firstly, PSO optimizes an irregular polygonal infrared patch to attack the infrared detector; secondly, the color QR code is optimized, and the shape information of the infrared patch from the first stage is used as a mask. The resulting irregular polygon visible modal patch executes an attack on the visible detector. Through extensive experiments conducted in both digital and physical environments, we validate the effectiveness and robustness of the proposed method. As the TOUAP surpasses baseline performance, we advocate for its widespread attention.

Chengyin Hu, Yuxian Dong, Yikun Guo et al.

Infrared vision-language models (IR-VLMs) have emerged as a promising paradigm for multimodal perception in low-visibility environments, yet their robustness to adversarial attacks remains largely unexplored. Existing adversarial patch methods are mainly designed for RGB-based models in closed-set settings and are not readily applicable to the open-ended semantic understanding and physical deployment requirements of infrared VLMs. To bridge this gap, we propose Universal Curved-Grid Patch (UCGP), a universal physical adversarial patch framework for IR-VLMs. UCGP integrates Curved-Grid Mesh (CGM) parameterization for continuous, low-frequency, and deployable patch generation with a unified representation-driven objective that promotes subspace departure, topology disruption, and stealth. To improve robustness under real-world deployment and domain shift, we further incorporate Meta Differential Evolution and EOT-augmented TPS deformation modeling. Rather than manipulating labels or prompts, UCGP directly disrupts the visual representation space, weakening cross-modal semantic alignment. Extensive experiments demonstrate that UCGP consistently compromises semantic understanding across diverse IR-VLM architectures while maintaining cross-model transferability, cross-dataset generalization, real-world physical effectiveness, and robustness against defenses. These findings reveal a previously overlooked robustness vulnerability in current infrared multimodal systems.

Chengyin Hu, Xiang Chen, Zhe Jia et al.

Vision-Language Models (VLMs) are trained on image-text pairs collected under canonical visual conditions and achieve strong performance on multimodal tasks. However, their robustness to real-world weather conditions, and the stability of cross-modal semantic alignment under such structured perturbations, remain insufficiently studied. In this paper, we focus on rainy scenarios and introduce the first adversarial framework that exploits realistic weather to attack VLMs, using a two-stage, parameterized perturbation model based on semantic decoupling to analyze rain-induced shifts in decision-making. In Stage 1, we model the global effects of rainfall by applying a low-dimensional global modulation to condition the embedding space and gradually weaken the original semantic decision boundaries. In Stage 2, we introduce structured rain variations by explicitly modeling multi-scale raindrop appearance and rainfall-induced illumination changes, and optimize the resulting non-differentiable weather space to induce stable semantic shifts. Operating in a non-pixel parameter space, our framework generates perturbations that are both physically grounded and interpretable. Experiments across multiple tasks show that even physically plausible, highly constrained weather perturbations can induce substantial semantic misalignment in mainstream VLMs, posing potential safety and reliability risks in real-world deployment. Ablations further confirm that illumination modeling and multi-scale raindrop structures are key drivers of these semantic shifts.

Chengyin Hu, Weiwen Shi, Chao Li et al.

Deep neural networks (DNNs) have made remarkable strides in various computer vision tasks, including image classification, segmentation, and object detection. However, recent research has revealed a vulnerability in advanced DNNs when faced with deliberate manipulations of input data, known as adversarial attacks. Moreover, the accuracy of DNNs is heavily influenced by the distribution of the training dataset. Distortions or perturbations in the color space of input images can introduce out-of-distribution data, resulting in misclassification. In this work, we propose a brightness-variation dataset, which incorporates 24 distinct brightness levels for each image within a subset of ImageNet. This dataset enables us to simulate the effects of light and shadow on the images, so as is to investigate the impact of light and shadow on the performance of DNNs. In our study, we conduct experiments using several state-of-the-art DNN architectures on the aforementioned dataset. Through our analysis, we discover a noteworthy positive correlation between the brightness levels and the loss of accuracy in DNNs. Furthermore, we assess the effectiveness of recently proposed robust training techniques and strategies, including AugMix, Revisit, and Free Normalizer, using the ResNet50 architecture on our brightness-variation dataset. Our experimental results demonstrate that these techniques can enhance the robustness of DNNs against brightness variation, leading to improved performance when dealing with images exhibiting varying brightness levels.