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

美
美团技术团队
Blog — PlanetScale
Blog — PlanetScale
阮一峰的网络日志
阮一峰的网络日志
M
MIT News - Artificial intelligence
月光博客
月光博客
钛媒体：引领未来商业与生活新知
钛媒体：引领未来商业与生活新知
U
Unit 42
博
博客园_首页
WordPress大学
WordPress大学
H
Hackread – Cybersecurity News, Data Breaches, AI and More
J
Java Code Geeks
F
Fortinet All Blogs
腾
腾讯CDC
罗
罗磊的独立博客
IT之家
IT之家
I
InfoQ
V
V2EX
博
博客园 - 叶小钗
A
About on SuperTechFans
Y
Y Combinator Blog
C
Check Point Blog
量
量子位
Martin Fowler
Martin Fowler
Vercel News
Vercel News

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
Uncovering and Mitigating Destructive Multi-Embedding Att...
Lixin Jia, H · 2026-03-14 · via Proceedings of the AAAI Conference on Artificial Intelligence

Authors

  • Lixin Jia School of Computer Science and Technology, Xinjiang University
  • Haiyang Sun School of Computer Science and Technology, Xinjiang University
  • Zhiqing Guo School of Computer Science and Technology, Xinjiang University Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center
  • Yunfeng Diao School of Computer Science and Information Engineering, Hefei University of Technology
  • Dan Ma School of Computer Science and Technology, Xinjiang University
  • Gaobo Yang College of Computer Science and Electronic Engineering, Hunan University

DOI:

https://doi.org/10.1609/aaai.v40i1.37010

Abstract

With the rapid evolution of deepfake technologies and the wide dissemination of digital media, personal privacy is facing increasingly serious security threats. Deepfake proactive forensics, which involves embedding imperceptible watermarks to enable reliable source tracking, serves as a crucial defense against these threats. Although existing methods show strong forensic ability, they rely on an idealized assumption of single watermark embedding, which proves impractical in real-world scenarios. In this paper, we formally define and demonstrate the existence of Multi-Embedding Attacks (MEA) for the first time. When a previously protected image undergoes additional rounds of watermark embedding, the original forensic watermark can be destroyed or removed, rendering the entire proactive forensic mechanism ineffective. To address this vulnerability, we propose a general training paradigm named Adversarial Interference Simulation (AIS). Rather than modifying the network architecture, AIS explicitly simulates MEA scenarios during fine-tuning and introduces a resilience-driven loss function to enforce the learning of sparse and stable watermark representations. Our method enables the model to maintain the ability to extract the original watermark correctly even after a second embedding. Extensive experiments demonstrate that our plug-and-play AIS training paradigm significantly enhances the robustness of various existing methods against MEA.

How to Cite

Jia, L., Sun, H., Guo, Z., Diao, Y., Ma, D., & Yang, G. (2026). Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 471–479. https://doi.org/10.1609/aaai.v40i1.37010

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。