exploiting cdeepfuzz backdoors naturally
【五期邹昱夫】CCF-B（IEEE Access'19）Badnets: Evaluating backdooring attacks on deep neural networks
> "Gu, Tianyu, et al. "Badnets: Evaluating backdooring attacks on deep neural networks." IEEE Access 7 (2019): 47230-47244." 本文提出了外包机器学习时选择值得信赖的提供商的重要 ......
【五期邹昱夫】CCF-B（RAID'18）Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
> "Liu, Kang, Brendan Dolan-Gavitt, and Siddharth Garg. "Fine-pruning: Defending against backdooring attacks on deep neural networks." Research in Att ......
【五期邹昱夫】CCF-A（NeurIPS'22）Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork
> "Wang, Haotao, et al. "Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork." Advances in Neural Informa ......
【五期邹昱夫】CCF-A（NeurIPS'21）Adversarial Neuron Pruning Purifies Backdoored Deep Models
> "Wu, Dongxian, and Yisen Wang. "Adversarial neuron pruning purifies backdoored deep models." Advances in Neural Information Processing Systems 34 (2 ......
[6] Fast and Practical Secret Key Extraction by Exploiting Channel Response 论文精读 INFOCOM 13'
摘要 摘要写的很清楚，几句话说明了当前密钥发展现状，即使用RSS为基础的密钥生成解决方案的生成速率有待提升，因此本文主打一个高速率；此外本文提出了CGC算法来解决现实生活中的信道互易性差的问题；此外，其能够抵御被认为对RSS技术有害的恶意攻击！ 但是他的Abstract我有一点不满哈，全文都是CSI ......
Helping the Nature
给出一个长度为 n 的序列 a，每次可以进行三种操作中的一种： 选择 i，将 1,2,⋯ ,a1,a2,⋯,ai 减 1。 选择 i，将 ,+1,⋯ ,ai,ai+1,⋯,an 减 1。 将所有 ai 加 1。 求最少需要多少次操作将所有 ai 变为 0。 1≤2×1041≤T≤2× ......
nature-deep learning
Title：Deep learning Authors：Yann LeCun Yoshua Bengio & Geoffrey Hinton doi:10.1038/nature14539 # 1. 概述 使用多处理层学习数据不同层次的抽象表示，在语音识别、视觉识别、目标检测，以及药物发明、基因学等 ......
Exploiting Positional Information for Session-based Recommendation
[TOC] > [Qiu R., Huang Z., Chen T. and Yin H. Exploiting positional information for session-based recommendation. ACM Transactions on Information Syst ......
Post-Exploitation Basics
开发后基础知识 https://tryhackme.com/room/postexploit 使用 mimikatz、bloodhound、powerview 和 msfvenom 学习后期开发和维护访问的基础知识 # 介绍 从使用 powerview 和 bloodhound 进行后开发枚举，使用 ......
EME 15 Nature of SEE
Nature of SEE Definition of SEE Software Engineering Economics The application of economic theory and methods to software engineering business decisio ......
Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference
Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference 论文全程及链接：《Exploiting Cloze Questions for Few Shot Text Class ......
迁移学习（NRC）《Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation》
论文信息 论文标题：Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation论文作者：Shiqi YangYaxing WangJoost van de WeijerLuis HerranzSh ......