バックドアモデルの検知

Model-agnostic clean-label backdoor mitigation in cybersecurity environments

Authors: Giorgio Severi, Simona Boboila, John Holodnak, Kendra Kratkiewicz, Rauf Izmailov, Michael J. De Lucia, Alina Oprea | Published: 2024-07-11 | Updated: 2025-05-05
バックドアモデルの検知
バックドア攻撃
防御メカニズム

Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning

Authors: Shuai Zhao, Leilei Gan, Luu Anh Tuan, Jie Fu, Lingjuan Lyu, Meihuizi Jia, Jinming Wen | Published: 2024-02-19 | Updated: 2024-03-29
バックドアモデルの検知
攻撃手法
防御手法

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

T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification

Authors: Ahmadreza Azizi, Ibrahim Asadullah Tahmid, Asim Waheed, Neal Mangaokar, Jiameng Pu, Mobin Javed, Chandan K. Reddy, Bimal Viswanath | Published: 2021-03-07 | Updated: 2021-03-11
テキストの摂動手法
バックドアモデルの検知
攻撃手法

ONION: A Simple and Effective Defense Against Textual Backdoor Attacks

Authors: Fanchao Qi, Yangyi Chen, Mukai Li, Yuan Yao, Zhiyuan Liu, Maosong Sun | Published: 2020-11-20 | Updated: 2021-11-03
テキストの摂動手法
トリガーの検知
バックドアモデルの検知

Backdoor Attacks to Graph Neural Networks

Authors: Zaixi Zhang, Jinyuan Jia, Binghui Wang, Neil Zhenqiang Gong | Published: 2020-06-19 | Updated: 2021-12-17
バックドアモデルの検知
バックドア攻撃
防御手法

Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems

Authors: Bao Gia Doan, Ehsan Abbasnejad, Damith C. Ranasinghe | Published: 2019-08-09 | Updated: 2020-09-28
トリガーの検知
トロイの木馬検出
バックドアモデルの検知

Supervised Machine Learning Techniques for Trojan Detection with Ring Oscillator Network

Authors: Kyle Worley, Md Tauhidur Rahman | Published: 2019-03-12
ハードウェアセキュリティ
バックドアモデルの検知
マルチクラス分類

Mockingbird: Defending Against Deep-Learning-Based Website Fingerprinting Attacks with Adversarial Traces

Authors: Mohammad Saidur Rahman, Mohsen Imani, Nate Mathews, Matthew Wright | Published: 2019-02-18 | Updated: 2020-10-28
バックドアモデルの検知
敵対的サンプル
敵対的攻撃手法

STRIP: A Defence Against Trojan Attacks on Deep Neural Networks

Authors: Yansong Gao, Chang Xu, Derui Wang, Shiping Chen, Damith C. Ranasinghe, Surya Nepal | Published: 2019-02-18 | Updated: 2020-01-17
トリガーの検知
トロイの木馬検出
バックドアモデルの検知