惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博
博客园 - 【当耐特】
Stack Overflow Blog
Stack Overflow Blog
V
Visual Studio Blog
小众软件
小众软件
The Cloudflare Blog
T
Tailwind CSS Blog
Apple Machine Learning Research
Apple Machine Learning Research
爱范儿
爱范儿
美
美团技术团队
WordPress大学
WordPress大学
罗
罗磊的独立博客
Microsoft Azure Blog
Microsoft Azure Blog
A
About on SuperTechFans
Last Week in AI
Last Week in AI
月光博客
月光博客
博
博客园 - Franky
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
G
Google Developers Blog
GbyAI
GbyAI
B
Blog
大猫的无限游戏
大猫的无限游戏
博
博客园 - 聂微东
Hugging Face - Blog
Hugging Face - Blog
博
博客园 - 叶小钗

Proceedings of the AAAI Conference on Artificial Intelligence

Resource Efficient Sleep Staging via Multi-Level Masking and Prompt Learning AutoMalDesc: Large-Scale Script Analysis for Cyber Threat Research Modulation-Based Backdoors: Leveraging Amplitude and Frequency Patterns to Attack Speaker Recognition Learning Structurally Stabilized Representations for Lossless DNA Storage ViG-RAG: Video-aware Graph Retrieval-Augmented Generation via Temporal and Semantic Hybrid Reasoning Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation Toward Multimodal Fake News Detection by Multi-perspective Rationale Generation and Verification RTMol: Rethinking Molecule-text Alignment in a Round-trip View Physical-regularized Hierarchical Generative Model for Metallic Glass Structural Generation and Energy Prediction Regressor-guided Diffusion Model for De Novo Peptide Sequencing with Explicit Mass Control RareAgents: Autonomous Multi-disciplinary Team for Rare Disease Diagnosis and Treatment Transferring Causal Driving Patterns for Generalizable Traffic Simulation with Diffusion-Based Distillation TRACE: Transformation-Aware Graph Refinement for Reaction Condition Prediction SIDE: Surrogate Conditional Data Extraction from Diffusion Models DyC-STG: Dynamic Causal Spatio-Temporal Graph Network for Real-time Data Credibility Analysis in IoT ProAR: Probabilistic Autoregressive Modeling for Molecular Dynamics Light but Sharp: SlimSTAD for Real-Time Action Detection from Sensor Data VFCionX: Bridging Large and Small Models for Robust Vulnerability-Fixing Commit Identification T2Agent: A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree Search Measuring What Matters: Scenario-Driven Evaluation for Trajectory Predictors in Autonomous Driving DensiCrafter: Physically-Constrained Generation and Fabrication of Self-Supporting Hollow Structures Topology-Enhanced and Label Correlation-Aware Model for Protein-Protein Interaction Prediction InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling NucEL: Single-Nucleotide ELECTRA-Style Genomic Pre-training for Efficient and Interpretable Representations OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement Learning Learning from Long-Term Engagement: Adaptive Tutoring Dialogue Planning for Personalized Education Toward Time-Continuous Data Inference in Sparse Urban CrowdSensing Multi-Horizon Time Series Forecasting of Non-Parametric CDFs with Deep Lattice Networks From Stimuli to Minds: Enhancing Psychological Reasoning in LLMs via Bilateral Reinforcement Learning Unveiling the Attribute Misbinding Threat in Identity-Preserving Models
Stochastic Universal Adversarial Perturbations with Fixed...
Yulin Jin, X · 2026-03-14 · via Proceedings of the AAAI Conference on Artificial Intelligence

Authors

  • Yulin Jin Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University. The State Key Laboratory of Blockchain and Data Security, Zhejiang University.
  • Xiaoyu Zhang State Key Laboratory of ISN, Xidian University, Xi’an, Shaanxi, China. Key Laboratory of Data and Intelligent System Security Ministry of Education, China.
  • Haoyu Tong Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University.
  • Jian Lou State Key Laboratory of ISN, Xidian University, Xi’an, Shaanxi, China.
  • Kai Wu State Key Laboratory of ISN, Xidian University, Xi’an, Shaanxi, China.
  • Haibo Hu Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University. Research Centre for Privacy and Security Technologies in Future Smart Systems, The Hong Kong Polytechnic University.
  • Xiaofeng Chen State Key Laboratory of ISN, Xidian University, Xi’an, Shaanxi, China.

DOI:

https://doi.org/10.1609/aaai.v40i1.37015

Abstract

Adversarial perturbations (APs) have become a great concern in image classification tasks. The most challenging branch, universal adversarial perturbations (UAPs), are exploited to fool most of the unseen samples. Such one-to-all perturbations have the merit of transferability, which has strong practical significance. In this paper, we firstly define the transferability gap and the algorithm stability of the UAP algorithm, and prove the relationship between them. In analyzing the UAP algorithm stability, we prove that the convergence domain of existing UAP algorithms with dynamic constraints is excessively small, which degrades the capacity of UAPs. Thus, we further propose a new expected constraint and prove that UAPs in the expected constraint suit any sample in a high probability. Besides, we propose a Stochastic Universal Adversarial Perturbation (SUAP) that involves additive noise and the expected constraint. Finally, by treating the proposed algorithm as a stochastic differential equation, we prove an upper bound of the UAP algorithm stability of SUAP, which decreases exponentially at the beginning and then increases with a sublinear rate to at most a fixed constant. Experimental results show that SUAP is aligned with our analysis.

How to Cite

Jin, Y., Zhang, X., Tong, H., Lou, J., Wu, K., Hu, H., & Chen, X. (2026). Stochastic Universal Adversarial Perturbations with Fixed Optimization Constraint and Ensured High-probability Transferability. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 516–524. https://doi.org/10.1609/aaai.v40i1.37015

Issue

Section

AAAI Technical Track on Application Domains I

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。