Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the “pre-training & finetuning” learning paradigm significantly improves the VQA performance, the adversarial robustness of such a learning paradigm has not been explored. In this paper, we delve into a new problem: using a pre-trained multimodal source model to create adversarial image-text pairs and then transferring them to attack the target VQA models. Correspondingly, we propose a novel VQATTACK model, which can iteratively generate both im- age and text perturbations with the designed modules: the large language model (LLM)-enhanced image attack and the cross-modal joint attack module. At each iteration, the LLM-enhanced image attack module first optimizes the latent representation-based loss to generate feature-level image perturbations. Then it incorporates an LLM to further enhance the image perturbations by optimizing the designed masked answer anti-recovery loss. The cross-modal joint attack module will be triggered at a specific iteration, which updates the image and text perturbations sequentially. Notably, the text perturbation updates are based on both the learned gradients in the word embedding space and word synonym-based substitution. Experimental results on two VQA datasets with five validated models demonstrate the effectiveness of the proposed VQATTACK in the transferable attack setting, compared with state-of-the-art baselines. This work revealsa significant blind spot in the “pre-training & fine-tuning” paradigm on VQA tasks. The source code can be found in the link https://github.com/ericyinyzy/VQAttack.
This content will become publicly available on June 1, 2025
With recent advances in multi‐modal foundation models, the previously text‐only large language models (LLM) have evolved to incorporate visual input, opening up unprecedented opportunities for various applications in visualization. Compared to existing work on LLM‐based visualization works that generate and control visualization with textual input and output only, the proposed approach explores the utilization of the visual processing ability of multi‐modal LLMs to develop Autonomous Visualization Agents (AVAs) that can evaluate the generated visualization and iterate on the result to accomplish user‐defined objectives defined through natural language. We propose the first framework for the design of AVAs and present several usage scenarios intended to demonstrate the general applicability of the proposed paradigm. Our preliminary exploration and proof‐of‐concept agents suggest that this approach can be widely applicable whenever the choices of appropriate visualization parameters require the interpretation of previous visual output. Our study indicates that AVAs represent a general paradigm for designing intelligent visualization systems that can achieve high‐level visualization goals, which pave the way for developing expert‐level visualization agents in the future.
more » « less- Award ID(s):
- 2138811
- PAR ID:
- 10548488
- Publisher / Repository:
- Euro Graphics
- Date Published:
- Journal Name:
- Computer Graphics Forum
- Volume:
- 43
- Issue:
- 3
- ISSN:
- 0167-7055
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
-
Data visualizations help extract insights from datasets, but reaching these insights requires decomposing high level goals into low-level analytic tasks that can be complex due to varying degrees of data literacy and visualization experience. Recent advancements in large language models (LLMs) have shown promise for lowering barriers for users to achieve tasks such as writing code and may likewise facilitate visualization insight. Scalable Vector Graphics (SVG), a text-based image format common in data visualizations, matches well with the text sequence processing of transformer-based LLMs. In this paper, we explore the capability of LLMs to perform 10 low-level visual analytic tasks defined by Amar, Eagan, and Stasko directly on SVG-based visualizations. Using zero-shot prompts, we instruct the models to provide responses or modify the SVG code based on given visualizations. Our findings demonstrate that LLMs can effectively modify existing SVG visualizations for some tasks like Cluster but perform poorly on tasks requiring mathematical operations like Compute Derived Value. We also discovered that LLM performance can vary based on factors such as the number of data points, the presence of value labels, and the chart type. Our findings contribute to gauging the general capabilities of LLMs and highlight the need for further exploration and development to fully harness their potential in supporting visual analytic tasks.more » « less
-
Outside-knowledge visual question answering (OKVQA) requires the agent to comprehend the image, make use of relevant knowledge from the entire web, and digest all the information to answer the question. Most previous works address the problem by first fusing the image and question in the multi-modal space, which is inflexible for further fusion with a vast amount of external knowledge. In this paper, we call for an alternative paradigm for the OK-VQA task, which transforms the image into plain text, so that we can enable knowledge passage retrieval, and generative question-answering in the natural language space. This paradigm takes advantage of the sheer volume of gigantic knowledge bases and the richness of pretrained language models. A Transform-Retrieve-Generate framework (TRiG) framework is proposed, which can be plug-and-played with alternative image-to-text models and textual knowledge bases. Experimental results show that our TRiG framework outperforms all state-of-the-art supervised methods by at least 11.1% absolute margin.more » « less
-
Cyber-Physical Systems (CPS) are integrations of computation, networking, and physical processes. The autonomy and self-adaptation capabilities of CPS mark a significant evolution from traditional control systems. Machine learning significantly enhances the functionality and efficiency of Cyber-Physical Systems (CPS). Large Language Models (LLM), like GPT-4, can augment CPS’s functionality to a new level by providing advanced intelligence support. This fact makes the applications above potentially unsafe and thus untrustworthy if deployed to the real world. We propose a comprehensive and general assurance framework for LLM-enabled CPS. The framework consists of three modules: (i) the context grounding module assures the task context has been accurately grounded (ii) the temporal Logic requirements specification module forms the temporal requirements into logic specifications for prompting and further verification (iii) the formal verification module verifies the output of the LLM and provides feedback as a guideline for LLM. The three modules execute iteratively until the output of LLM is verified. Experiment results demonstrate that our assurance framework can assure the LLM-enabled CPS.more » « less
-
Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. Due to the impressive planning and reasoning abilities of LLMs, they have been used as autonomous agents to do many tasks automatically. Recently, based on the development of using one LLM as a single planning or decision-making agent, LLM-based multi-agent systems have achieved considerable progress in complex problem-solving and world simulation. To provide the community with an overview of this dynamic field, we present this survey to offer an in-depth discussion on the essential aspects of multi-agent systems based on LLMs, as well as the challenges. Our goal is for readers to gain substantial insights on the following questions: What domains and environments do LLM-based multi-agents simulate? How are these agents profiled and how do they communicate? What mechanisms contribute to the growth of agents' capacities? For those interested in delving into this field of study, we also summarize the commonly used datasets or benchmarks for them to have convenient access. To keep researchers updated on the latest studies, we maintain an open-source GitHub repository, dedicated to outlining the research on LLM-based multi-agent systems.more » « less
