防御手法

Membership Inference Attacks against Language Models via Neighbourhood Comparison

Authors: Justus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, Bernhard Schölkopf, Mrinmaya Sachan, Taylor Berg-Kirkpatrick | Published: 2023-05-29 | Updated: 2023-08-07
LLM性能評価
プライバシー保護手法
防御手法

COLLIDER: A Robust Training Framework for Backdoor Data

Authors: Hadi M. Dolatabadi, Sarah Erfani, Christopher Leckie | Published: 2022-10-13
コアセット選択手法
深層学習手法
防御手法

PUF-Phenotype: A Robust and Noise-Resilient Approach to Aid Intra-Group-based Authentication with DRAM-PUFs Using Machine Learning

Authors: Owen Millwood, Jack Miskelly, Bohao Yang, Prosanta Gope, Elif Kavun, Chenghua Lin | Published: 2022-07-11
アルゴリズム設計
モデルの設計や精度
防御手法

How many perturbations break this model? Evaluating robustness beyond adversarial accuracy

Authors: Raphael Olivier, Bhiksha Raj | Published: 2022-07-08 | Updated: 2023-08-10
モデルの設計や精度
敵対的訓練
防御手法

Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms

Authors: Ehsan Hallaji, Roozbeh Razavi-Far, Mehrdad Saif | Published: 2022-07-05
プライバシー保護
ポイズニング
防御手法

Defending against the Label-flipping Attack in Federated Learning

Authors: Najeeb Moharram Jebreel, Josep Domingo-Ferrer, David Sánchez, Alberto Blanco-Justicia | Published: 2022-07-05
アルゴリズム設計
ポイズニング
防御手法

Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems

Authors: Shail Dave, Alberto Marchisio, Muhammad Abdullah Hanif, Amira Guesmi, Aviral Shrivastava, Ihsen Alouani, Muhammad Shafique | Published: 2022-04-18
バックドア攻撃
メンバーシップ推論
防御手法

Machine Learning Security against Data Poisoning: Are We There Yet?

Authors: Antonio Emanuele Cinà, Kathrin Grosse, Ambra Demontis, Battista Biggio, Fabio Roli, Marcello Pelillo | Published: 2022-04-12 | Updated: 2024-03-08
ポイズニング
攻撃タイプ
防御手法

Breaking the De-Pois Poisoning Defense

Authors: Alaa Anani, Mohamed Ghanem, Lotfy Abdel Khaliq | Published: 2022-04-03
バックドア攻撃
ポイズニング
防御手法

Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning

Authors: Arezoo Rajabi, Bhaskar Ramasubramanian, Radha Poovendran | Published: 2022-03-25
トロイの木馬の署名
知識の蒸留
防御手法