Yanyun Wang's Gitbook
  • 👋Welcome to My Gitbook!
  • Reading Notes
    • Index Page
    • Reading Note: "Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming"
    • Reading Note: "Safety at Scale: A Comprehensive Survey of Large Model Safety"
    • Reading Note: "Towards More Practical Threat Models in Artificial Intelligence Security"
    • Reading Note: "A Survey on Neural Speech Synthesis"
    • Reading Note: "Threats to Pre-trained Language Models: Survey and Taxonomy"
    • Reading Note: "Survey: Leakage and Privacy at Inference Time"
    • Reading Note: "Membership Inference Attacks on Machine Learning: A Survey"
Powered by GitBook
On this page

Was this helpful?

  1. Reading Notes

Reading Note: "Safety at Scale: A Comprehensive Survey of Large Model Safety"

Ma et al. "Safety at Scale: A Comprehensive Survey of Large Model Safety". arXiv preprint arXiv:2502.05206 (2025).

PreviousReading Note: "Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming"NextReading Note: "Towards More Practical Threat Models in Artificial Intelligence Security"

Last updated 2 months ago

Was this helpful?

Intro

Range: Vision Foundation Models (VFMs), Large Language Models (LLMs), Vision-Language Pre-training (VLP) models, Vision-Language Models (VLMs), Diffusion Models (DMs), and large-model-based Agents.

Contributions:

  • Proposing a comprehensive taxonomy (10'): Adversarial, data poisoning, backdoor, jailbreak, prompt injection, energy-latency, membership inference, model extraction, data extraction, and agent-specific attacks.

  • Reviewing defense strategies and summarizing commonly used datasets and benchmarks.

  • Identifying and discussing open challenges: Comprehensive safety evaluations, scalable and effective defense mechanisms, and sustainable data practices.

The left part illustrates the quarterly trend in the number of safety research papers published across different models (in total 20, 24, 123, 223 papers from 2021-2024).