WaterMAS: Sharpness-Aware Maximization for Neural Network Watermarking

2024-09-05 · Carl De Sousa Trias, Mihai Mitrea, Attilio Fiandrotti, Marco Cagnazzo, Sumanta Chaudhuri, Enzo Tartaglione

Nowadays, deep neural networks are used for solving complex tasks in several critical applications and protecting both their integrity and intellectual property rights (IPR) has become of utmost importance. To this end, we advance WaterMAS, a substitutive, white-box neural network watermarking method that improves the trade-off among robustness, imperceptibility, and computational complexity, while making provisions for increased data payload and security. WasterMAS insertion keeps unchanged the watermarked weights while sharpening their underlying gradient space. The robustness is thus ensured by limiting the attack's strength: even small alterations of the watermarked weights would impact the model's performance. The imperceptibility is ensured by inserting the watermark during the training process. The relationship among the WaterMAS data payload, imperceptibility, and robustness properties is discussed. The secret key is represented by the positions of the weights conveying the watermark, randomly chosen through multiple layers of the model. The security is evaluated by investigating the case in which an attacker would intercept the key. The experimental validations consider 5 models and 2 tasks (VGG16, ResNet18, MobileNetV3, SwinT for CIFAR10 image classification, and DeepLabV3 for Cityscapes image segmentation) as well as 4 types of attacks (Gaussian noise addition, pruning, fine-tuning, and quantization). The code will be released open-source upon acceptance of the article.

📄 PDF Abstract BibTeX arXiv:2409.03902

Code (0)

등록된 구현이 없습니다.

Tasks

image-classification Image Classification Image Segmentation Quantization Semantic Segmentation

Methods 이 논문이 사용한 방법론

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…

Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …

Sigmoid Activation 설명 없음

Spatial Pyramid Pooling Spatial Pyramid Pooling (SPP) is a pooling layer that removes the fixed-size constraint of the network, i.e. a CNN does not require a fixed-size input image. Specifically, we…

Average Pooling 설명 없음

ASPP Atrous Spatial Pyramid Pooling (ASPP) is a semantic segmentation module for resampling a given feature layer at multiple rates prior to…

WaterMask: Instance Segmentation for Underwater Imagery

2023-01-01 · ICCV 2023 1 · Shijie Lian, Hua Li, Runmin Cong, Suqi Li 외

Underwater image instance segmentation is a fundamental and critical step in underwater image analysis and understanding. However, the paucity of general multiclass instance segmentation datasets has impeded the deve…

2D Object Detection Graph Attention Instance Segmentation Segmentation+1

Lookbehind-SAM: k steps back, 1 step forward

2023-07-31 · Gonçalo Mordido, Pranshu Malviya, Aristide Baratin, Sarath Chandar

Sharpness-aware minimization (SAM) methods have gained increasing popularity by formulating the problem of minimizing both loss value and loss sharpness as a minimax objective. In this work, we increase the efficiency of…

Lifelong learning

Sharpness-Aware Machine Unlearning

2025-06-16 · Haoran Tang, Rajiv Khanna

We characterize the effectiveness of Sharpness-aware minimization (SAM) under machine unlearning scheme, where unlearning forget signals interferes with learning retain signals. While previous work prove that SAM improve…

Denoising Machine Unlearning Memorization

Model Generalization: A Sharpness Aware Optimization Perspective

2022-08-14 · Jozef Marus Coldenhoff, Chengkun Li, Yurui Zhu

Sharpness-Aware Minimization (SAM) and adaptive sharpness-aware minimization (ASAM) aim to improve the model generalization. And in this project, we proposed three experiments to valid their generalization from the sharp…

model valid

ESSAM: A Novel Competitive Evolution Strategies Approach to Reinforcement Learning for Memory Efficient LLMs Fine-Tuning

2026-02-01 · Zhishen Sun, Sizhe Dang, Guang Dai, Haishan Ye arxiv

Reinforcement learning (RL) has become a key training step for improving mathematical reasoning in large language models (LLMs), but it often has high GPU memory usage, which makes it hard to use in settings with limited…

Reinforcement Learning Mathematical Reasoning