亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

SecureNet: Proactive intellectual property protection and model security defense for DNNs based on backdoor learning

后门 计算机科学 钥匙(锁) 许可证 计算机安全 知识产权 人工智能 机器学习 操作系统
作者
Peihao Li,Jie Huang,Huaqing Wu,Zeping Zhang,Chunyang Qi
出处
期刊:Neural Networks [Elsevier BV]
卷期号:: 106199-106199
标识
DOI:10.1016/j.neunet.2024.106199
摘要

With the widespread application of deep neural networks (DNNs), the risk of privacy breaches against DNN models is constantly on the rise, resulting in an increasing need for intellectual property (IP) protection for such models. Although neural network watermarking techniques are widely used to safeguard the IP of DNNs, they can only achieve passive protection and cannot actively prevent unauthorized users from illicit use or embezzlement of the trained DNN models. Therefore, the development of proactive protection techniques to prevent IP infringement is imperative. To this end, we propose SecureNet, a key-based access license framework for DNN models. The proposed approach involves injecting license keys into the model through backdoor learning, enabling correct model functionality only when the appropriate license key is included in the input. To ensure the reusability of DNN models, we also propose a license key replacement algorithm. In addition, based on SecureNet, we designed defense mechanisms against adversarial attacks and backdoor attacks, respectively. Furthermore, we introduce a fine-grained authorization method that enables flexible granting of model permissions to different users. We have designed four license-key schemes with different privileges, tailored to various scenarios. We evaluated SecureNet on five benchmark datasets including MNIST, Cifar10, Cifar100, FaceScrub, and CelebA, and assessed its performance on six classic DNN models: LeNet-5, VGG16, ResNet18, ResNet101, NFNet-F5, and MobileNetV3. The results demonstrate that our approach outperforms the state-of-the-art model parameter encryption methods by at least 95% in terms of computational efficiency. Additionally, it provides effective defense against adversarial attacks and backdoor attacks without compromising the model’s overall performance.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
8秒前
lijiawei发布了新的文献求助10
10秒前
Criminology34发布了新的文献求助50
12秒前
睡觉补充能量完成签到,获得积分10
12秒前
fengfenghao完成签到,获得积分10
18秒前
小凯完成签到 ,获得积分10
21秒前
jueshadi完成签到 ,获得积分10
21秒前
朵朵完成签到,获得积分10
23秒前
28秒前
32秒前
dong发布了新的文献求助10
33秒前
35秒前
35秒前
35秒前
aaaaal发布了新的文献求助10
37秒前
39秒前
annaanna完成签到 ,获得积分10
41秒前
Criminology34发布了新的文献求助50
43秒前
ccc完成签到 ,获得积分10
43秒前
45秒前
YY发布了新的文献求助10
45秒前
Gin发布了新的文献求助10
48秒前
aaaaal完成签到,获得积分10
48秒前
Becky完成签到 ,获得积分10
51秒前
52秒前
杨北风完成签到 ,获得积分20
52秒前
科研通AI6应助科研通管家采纳,获得10
53秒前
54秒前
共享精神应助科研通管家采纳,获得10
54秒前
54秒前
所所应助科研通管家采纳,获得10
54秒前
54秒前
54秒前
Hello应助科研通管家采纳,获得10
54秒前
小蘑菇应助科研通管家采纳,获得10
54秒前
54秒前
ye发布了新的文献求助20
57秒前
58秒前
59秒前
Abu完成签到 ,获得积分10
1分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Architectural Corrosion and Critical Infrastructure 1000
Early Devonian echinoderms from Victoria (Rhombifera, Blastoidea and Ophiocistioidea) 1000
By R. Scott Kretchmar - Practical Philosophy of Sport and Physical Activity - 2nd (second) Edition: 2nd (second) Edition 666
Electrochemistry: Volume 17 600
Physical Chemistry: How Chemistry Works 500
SOLUTIONS Adhesive restoration techniques restorative and integrated surgical procedures 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 内科学 生物化学 物理 计算机科学 纳米技术 遗传学 基因 复合材料 化学工程 物理化学 病理 催化作用 免疫学 量子力学
热门帖子
关注 科研通微信公众号,转发送积分 4944655
求助须知:如何正确求助?哪些是违规求助? 4209521
关于积分的说明 13085355
捐赠科研通 3989302
什么是DOI,文献DOI怎么找? 2184055
邀请新用户注册赠送积分活动 1199418
关于科研通互助平台的介绍 1112457