文献データベース

Vulnerability of Machine Learning Approaches Applied in IoT-based Smart Grid: A Review

Authors: Zhenyong Zhang, Mengxiang Liu, Mingyang Sun, Ruilong Deng, Peng Cheng, Dusit Niyato, Mo-Yuen Chow, Jiming Chen | Published: 2023-08-30 | Updated: 2023-12-25
エネルギー管理
プロンプトインジェクション
敵対的訓練

Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation

Authors: Jiachen T. Wang, Yuqing Zhu, Yu-Xiang Wang, Ruoxi Jia, Prateek Mittal | Published: 2023-08-30 | Updated: 2023-11-26
データ生成
プライバシー保護手法
計算効率

Predict And Prevent DDOS Attacks Using Machine Learning and Statistical Algorithms

Authors: Azadeh Golduzian | Published: 2023-08-30
DDoS攻撃
機械学習手法
特徴の相互依存性

Adaptive Attack Detection in Text Classification: Leveraging Space Exploration Features for Text Sentiment Classification

Authors: Atefeh Mahdavi, Neda Keivandarian, Marco Carvalho | Published: 2023-08-29
テキスト生成手法
敵対的訓練
適応型誤用検出

On the Steganographic Capacity of Selected Learning Models

Authors: Rishit Agrawal, Kelvin Jou, Tanush Obili, Daksh Parikh, Samarth Prajapati, Yash Seth, Charan Sridhar, Nathan Zhang, Mark Stamp | Published: 2023-08-29
データ生成
機械学習手法
透かしの耐久性

Gender bias and stereotypes in Large Language Models

Authors: Hadas Kotek, Rikker Dockum, David Q. Sun | Published: 2023-08-28
AIによる出力のバイアスの検出
アルゴリズムの公平性
大規模言語モデル

Generating tabular datasets under differential privacy

Authors: Gianluca Truda | Published: 2023-08-28
データ生成
プライバシー保護
プライバシー保護手法

Are Existing Out-Of-Distribution Techniques Suitable for Network Intrusion Detection?

Authors: Andrea Corsini, Shanchieh Jay Yang | Published: 2023-08-28
Out-of-Distribution検出
未知の攻撃検出
機械学習手法

Detecting Language Model Attacks with Perplexity

Authors: Gabriel Alon, Michael Kamfonas | Published: 2023-08-27 | Updated: 2023-11-07
LLMセキュリティ
プロンプトインジェクション
悪意のあるプロンプト

LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors

Authors: Chengkun Wei, Wenlong Meng, Zhikun Zhang, Min Chen, Minghu Zhao, Wenjing Fang, Lei Wang, Zihui Zhang, Wenzhi Chen | Published: 2023-08-26 | Updated: 2023-10-14
トリガーの検知
バックドアモデルの検知
攻撃手法