Deep learning (DL) models have become one of the most valuable assets in modern society, and those most complex ones require millions of dollars for the model development. As a result, unauthorized ...duplication or reproduction of DL models can lead to copyright infringement and cause huge economic losses to model owners.
In this work, we present DeepJudge, a testing framework for DL copyright protection. DeepJudge quantitatively tests the similarities between two DL models: a victim model and a suspect model. It leverages a diverse set of testing metrics and efficient test case generation algorithms to produce a chain of supporting evidence to help determine whether a suspect model is a copy of the victim model. Our experiments confirm the effectiveness of DeepJudge under typical model copyright infringement scenarios. The tool has been made publicly available at https://github.com/Testing4AI/DeepJudge. A demo video can be found at https://www.youtube.com/watch?v=LhNeo615YOE.
This short note elaborates a concise protocol for the synthesis of two novel vicinal haloethers bearing a malonontrile group, 2-bromo-2-(methoxy(phenyl)methyl)malononitrile (1) and ...2-iodo-2-(methoxy(phenyl)methyl)malononitrile (2). The structures of the synthesized compounds were confirmed by 1H, 13C-NMR spectroscopy. The final products indicate that methanol not only acts as solvent but also participates in and dominates the reaction result.
Deep learning models, especially those large-scale and high-performance ones, can be very costly to train, demanding a considerable amount of data and computational resources. As a result, deep ...learning models have become one of the most valuable assets in modern artificial intelligence. Unauthorized duplication or reproduction of deep learning models can lead to copyright infringement and cause huge economic losses to model owners, calling for effective copyright protection techniques. Existing protection techniques are mostly based on watermarking, which embeds an owner-specified watermark into the model. While being able to provide exact ownership verification, these techniques are 1) invasive, i.e., they need to tamper with the training process, which may affect the model utility or introduce new security risks into the model; 2) prone to adaptive attacks that attempt to remove/replace the watermark or adversarially block the retrieval of the watermark; and 3) not robust to the emerging model extraction attacks. Latest fingerprinting work on deep learning models, though being non-invasive, also falls short when facing the diverse and ever-growing attack scenarios.In this paper, we propose a novel testing framework for deep learning copyright protection: DEEPJUDGE. DEEPJUDGE quantitatively tests the similarities between two deep learning models: a victim model and a suspect model. It leverages a diverse set of testing metrics and efficient test case generation algorithms to produce a chain of supporting evidence to help determine whether a suspect model is a copy of the victim model. Advantages of DEEPJUDGE include: 1) non-invasive, as it works directly on the model and does not tamper with the training process; 2) efficient, as it only needs a small set of seed test cases and a quick scan of the two models; 3) flexible, i.e., it can easily incorporate new testing metrics or test case generation methods to obtain more confident and robust judgement; and 4) fairly robust to model extraction attacks and adaptive attacks. We verify the effectiveness of DEEPJUDGE under three typical copyright infringement scenarios, including model finetuning, pruning and extraction, via extensive experiments on both image classification and speech recognition datasets with a variety of model architectures.
As a good substrate, silk fibers are widely employed in the field of intelligent textiles. In this work, the surface of silk fibers were firstly roughened by formic acid and sensitized by tannic ...acid, and then the silver ammonia solution was reduced by glucose to synthesize nano-silver in situ on the silk surface to obtain composite conductive silk fibers with resistivity as low as 0.24 mΩ·cm. It was proved by scanning electron microscope (SEM), energy-dispersive X-ray spectroscopy (EDS), X-ray diffraction (XRD), and X-ray photoelectron spectroscopy (XPS) tests that a uniformly deposited nano-silver layer was fabricated on the silk surface. The prepared silk fibers had stable mechanical, thermal, electrical, and antibacterial properties and can be used for human sensing.
Display omitted
Recent breakthroughs in Artificial Intelligence, Deep Learning, and Document Image Analysis and Recognition have significantly eased the creation of digital libraries and the transcription of ...historical documents. However, for documents in rare scripts with few labelled training data available, current Handwritten Text Recognition (HTR) systems are too constraining. Moreover, research on HTR often focuses on technical aspects only, and rarely puts emphasis on implementing software tools for scholars in Humanities. In this article, we describe, compare, and analyse different transcription methods for rare scripts. We evaluate their performance in a real-use case of a medieval manuscript written in the runic script (Codex Runicus) and discuss advantages and disadvantages of each method from the user perspective. From this exhaustive analysis and comparison with a fully manual transcription, we raise conclusions and provide recommendations to scholars interested in using automatic transcription tools.
This paper investigates the effectiveness of different deep learning HTR families, including LSTM, Seq2Seq, and transformer-based approaches with self-supervised pretraining, in recognizing ciphered ...manuscripts from different historical periods and cultures. The goal is to identify the most suitable method or training techniques for recognizing ciphered manuscripts and to provide insights into the challenges and opportunities in this field of research. We evaluate the performance of these models on several datasets of ciphered manuscripts and discuss their results. This study contributes to the development of more accurate and efficient methods for recognizing historical manuscripts for the preservation and dissemination of our cultural heritage.
As a remarkable advancement in signal processing, compressed sensing (CS) has proven to be valuable in source-limited applications, such as magnetic resonance imaging and computational imaging. Due ...to its capability to meet the requirements for real-time applications, deep learning-based reconstruction for block-based image CS has recently become a hot topic. However, the existing deep learning-based methods suffer from blocking artifacts, and have limited reconstruction performance due to ignoring the lost information during block-based measurement. To address these problems, this paper proposes a normalizing flow-based network for block-based image CS reconstruction, dubbed NF-BCSNet. NF-BCSNet fully utilizes the invertible property of normalizing flow to model the lost information during block-based measurement through a progressive architecture. To be specific, NF-BCSNet utilizes a combination of multi-level high-frequency information and low-frequency information that is both case-agnostic to model the lost information. Meanwhile, instead of reconstructing each block independently, NF -BCSNet reconstructs blocks simultaneously to fully exploit inter-block correlation. According to the simulation results, NF-BCSNet effectively alleviates blocking artifacts, and outperforms the other state-of-the-art methods in terms of reconstruction quality.
Assessing the physical condition in rehabilitation scenarios is a challenging problem, since it involves Human Activity Recognition (HAR) and kinematic analysis methods. In addition, the difficulties ...increase in unconstrained rehabilitation scenarios, which are much closer to the real use cases. In particular, our aim is to design an upper-limb assessment pipeline for stroke patients using smartwatches. We focus on the HAR task, as it is the first part of the assessing pipeline. Our main target is to automatically detect and recognize four key movements inspired by the Fugl-Meyer assessment scale, which are performed in both constrained and unconstrained scenarios. In addition to the application protocol and dataset, we propose two detection and classification baseline methods. We believe that the proposed framework, dataset and baseline results will serve to foster this research field.