A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations

• URL: http://arxiv.org/abs/2502.14881v1
• Date: Fri, 14 Feb 2025 08:42:43 GMT
• Title: A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
• Authors: Mang Ye, Xuankun Rong, Wenke Huang, Bo Du, Nenghai Yu, Dacheng Tao,
• Abstract summary: This survey provides a comprehensive analysis of LVLM safety, covering key aspects such as attacks, defenses, and evaluation methods.<n>We introduce a unified framework that integrates these interrelated components, offering a holistic perspective on the vulnerabilities of LVLMs.<n>We conduct a set of safety evaluations on the latest LVLM, Deepseek Janus-Pro, and provide a theoretical analysis of the results.
• Score: 127.52707312573791
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rapid advancement of Large Vision-Language Models (LVLMs), ensuring their safety has emerged as a crucial area of research. This survey provides a comprehensive analysis of LVLM safety, covering key aspects such as attacks, defenses, and evaluation methods. We introduce a unified framework that integrates these interrelated components, offering a holistic perspective on the vulnerabilities of LVLMs and the corresponding mitigation strategies. Through an analysis of the LVLM lifecycle, we introduce a classification framework that distinguishes between inference and training phases, with further subcategories to provide deeper insights. Furthermore, we highlight limitations in existing research and outline future directions aimed at strengthening the robustness of LVLMs. As part of our research, we conduct a set of safety evaluations on the latest LVLM, Deepseek Janus-Pro, and provide a theoretical analysis of the results. Our findings provide strategic recommendations for advancing LVLM safety and ensuring their secure and reliable deployment in high-stakes, real-world applications. This survey aims to serve as a cornerstone for future research, facilitating the development of models that not only push the boundaries of multimodal intelligence but also adhere to the highest standards of security and ethical integrity. Furthermore, to aid the growing research in this field, we have created a public repository to continuously compile and update the latest work on LVLM safety: https://github.com/XuankunRong/Awesome-LVLM-Safety .

Related papers

• A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment [291.03029298928857]
  This paper introduces the concept of "full-stack" safety to systematically consider safety issues throughout the entire process of LLM training, deployment, and commercialization. Our research is grounded in an exhaustive review of over 800+ papers, ensuring comprehensive coverage and systematic organization of security issues. Our work identifies promising research directions, including safety in data generation, alignment techniques, model editing, and LLM-based agent systems.
  arXiv  Detail & Related papers  (2025-04-22T05:02:49Z)
• When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs [15.74045364570382]
  We present an in-depth survey of the attack strategies tailored for Vision-Language Models (VLMs)<n>We categorize these attacks based on their underlying objectives.<n>We outline corresponding defense mechanisms that have been proposed to mitigate these vulnerabilities.
  arXiv  Detail & Related papers  (2025-02-10T12:20:08Z)
• Large Language Model Safety: A Holistic Survey [35.42419096859496]
  The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence.<n>This survey provides a comprehensive overview of the current landscape of LLM safety, covering four major categories: value misalignment, robustness to adversarial attacks, misuse, and autonomous AI risks.
  arXiv  Detail & Related papers  (2024-12-23T16:11:27Z)
• A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends [78.3201480023907]
  Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a wide range of multimodal understanding and reasoning tasks. The vulnerability of LVLMs is relatively underexplored, posing potential security risks in daily usage. In this paper, we provide a comprehensive review of the various forms of existing LVLM attacks.
  arXiv  Detail & Related papers  (2024-07-10T06:57:58Z)
• AI Safety in Generative AI Large Language Models: A Survey [14.737084887928408]
  Large Language Model (LLMs) that exhibit generative AI capabilities are facing accelerated adoption and innovation. Generative AI (GAI) inevitably raises concerns about the risks and safety associated with these models. This article provides an up-to-date survey of recent trends in AI safety research of GAI-LLMs from a computer scientist's perspective.
  arXiv  Detail & Related papers  (2024-07-06T09:00:18Z)
• Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward [9.218557081971708]
  Large Language Models (LLMs) have seen widespread applications across numerous fields. Their limited interpretability poses concerns regarding their safe operations from multiple aspects. Recent research has started developing quality assurance methods for LLMs.
  arXiv  Detail & Related papers  (2024-04-12T14:55:16Z)
• SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models [107.82336341926134]
  SALAD-Bench is a safety benchmark specifically designed for evaluating Large Language Models (LLMs) It transcends conventional benchmarks through its large scale, rich diversity, intricate taxonomy spanning three levels, and versatile functionalities.
  arXiv  Detail & Related papers  (2024-02-07T17:33:54Z)
• The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness [56.174255970895466]
  Large Language Models (LLMs) play an increasingly pivotal role in natural language processing applications. This paper presents Safety and Over-Defensiveness Evaluation (SODE) benchmark.
  arXiv  Detail & Related papers  (2023-12-30T17:37:06Z)
• Safety Assessment of Chinese Large Language Models [51.83369778259149]
  Large language models (LLMs) may generate insulting and discriminatory content, reflect incorrect social values, and may be used for malicious purposes. To promote the deployment of safe, responsible, and ethical AI, we release SafetyPrompts including 100k augmented prompts and responses by LLMs.
  arXiv  Detail & Related papers  (2023-04-20T16:27:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.