相关论文: CBV: Clean-label Backdoor Attacks on Vision Langua…

Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities on Visual-Question-Answering (VQA) benchmarks. However, their robustness against textual misinformation remains under-explored. While existing research has…

Generative models are increasingly integrated into creative workflows. While text-to-image generation excels in visual quality and diversity, color accessibility for users with Color Vision Deficiencies (CVD) remains largely unexplored. Our…

Text-to-visualization (text-to-vis) models for tabular data have become essential tools in the era of big data, enabling users to generate visualizations and make data-driven decisions through natural language queries (NLQs). Despite their…

Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design strategies have been explored to attack text classifiers,…

Backdoor attack against image classification task has been widely studied and proven to be successful, while there exist little research on the backdoor attack against vision-language models. In this paper, we explore backdoor attack…

Vision-Language-Action (VLA) models map multimodal perception and language instructions to executable robot actions, making them particularly vulnerable to behavioral backdoor manipulation: a hidden trigger introduced during training can…

In this work, we introduce LLaDA-V, a purely diffusion-based Multimodal Large Language Model (MLLM) that integrates visual instruction tuning with masked diffusion models, representing a departure from the autoregressive paradigms dominant…

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

Backdoor attacks in the traditional graph neural networks (GNNs) field are easily detectable due to the dilemma of confusing labels. To explore the backdoor vulnerability of GNNs and create a more stealthy backdoor attack method, a…

Contrastive language-image pretraining (CLIP) has been found to be vulnerable to poisoning backdoor attacks where the adversary can achieve an almost perfect attack success rate on CLIP models by poisoning only 0.01\% of the training…

We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted misclassification, the goal is to induce systematic disruption that makes the model…

Diffusion models have attracted significant attention due to its exceptional data generation capabilities in fields such as image synthesis. However, recent studies have shown that diffusion models are vulnerable to copyright infringement…

Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…

The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol…

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Autoregressive (AR) vision-language models (VLMs) have long dominated multimodal understanding, reasoning, and graphical user interface (GUI) grounding. Recently, discrete diffusion vision-language models (DVLMs) have shown strong…

Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…

On-device Vision-Language Models (VLMs) promise data privacy via local execution. However, we show that the architectural shift toward Dynamic High-Resolution preprocessing (e.g., AnyRes) introduces an inherent algorithmic side-channel.…

Vision-language models (VLMs) are essential for contextual understanding of both visual and textual information. However, their vulnerability to adversarially manipulated inputs presents significant risks, leading to compromised outputs and…

Gathering enough images to train a deep computer vision model is a constant challenge. Unfortunately, collecting images from unknown sources can leave your model s behavior at risk of being manipulated by a dirty-label or clean-label attack…