paper-with-me

홈 › Papers

iNNformant: Boundary Samples as Telltale Watermarks

2021-06-14 · Alexander Schlögl, Tobias Kupek, Rainer Böhme

Boundary samples are special inputs to artificial neural networks crafted to identify the execution environment used for inference by the resulting output label. The paper presents and evaluates algorithms to generate transparent boundary samples. Transparency refers to a small perceptual distortion of the host signal (i.e., a natural input sample). For two established image classifiers, ResNet on FMNIST and CIFAR10, we show that it is possible to generate sets of boundary samples which can identify any of four tested microarchitectures. These sets can be built to not contain any sample with a worse peak signal-to-noise ratio than 70dB. We analyze the relationship between search complexity and resulting transparency.

📄 PDF Abstract BibTeX arXiv:2106.07303

Code (1)

alxshine/innformant 공식 구현 tf

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Batch Normalization 설명 없음
Residual Connection 설명 없음
Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Kaiming Initialization 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Similar Papers 제목 키워드 기반

Learning-Based Error Detection System for Advanced Vehicle Instrument Cluster Rendering

2024-09-04 · Cornelius Bürkle, Fabian Oboril, Kay-Ulrich Scholl

The automotive industry is currently expanding digital display options with every new model that comes onto the market. This entails not just an expansion in dimensions, resolution, and customization choices, but also th…

HarmonicAttack: An Adaptive Cross-Domain Audio Watermark Removal

2025-11-26 · Kexin Li, Xiao Hu, Ilya Grishchenko, David Lie arxiv

The availability of high-quality, AI-generated audio raises security challenges such as misinformation campaigns and voice-cloning fraud. A key defense against the misuse of AI-generated audio is by watermarking it, so t…

Fragile Model Watermark for integrity protection: leveraging boundary volatility and sensitive sample-pairing

2024-04-11 · Zhenzhe Gao, Zhenjun Tang, Zhaoxia Yin, Baoyuan Wu 외

Neural networks have increasingly influenced people's lives. Ensuring the faithful deployment of neural networks as designed by their model owners is crucial, as they may be susceptible to various malicious or unintentio…

DeepTracer: Tracing Stolen Model via Deep Coupled Watermarks

2025-11-12 · Yunfei Yang, Xiaojun Chen, Yuexin Xuan, Zhendong Zhao 외 arxiv

Model watermarking techniques can embed watermark information into the protected model for ownership declaration by constructing specific input-output pairs. However, existing watermarks are easily removed when facing mo…

BlockDoor: Blocking Backdoor Based Watermarks in Deep Neural Networks

2024-12-14 · Yi Hao Puah, Anh Tu Ngo, Nandish Chattopadhyay, Anupam Chattopadhyay

Adoption of machine learning models across industries have turned Neural Networks (DNNs) into a prized Intellectual Property (IP), which needs to be protected from being stolen or being used without authorization. This t…

Blocking