透かしの耐久性

Differential Privacy for Adaptive Weight Aggregation in Federated Tumor Segmentation

Authors: Muhammad Irfan Khan, Esa Alhoniemi, Elina Kontio, Suleiman A. Khan, Mojtaba Jafaritadi | Published: 2023-08-01
医療データの透かし設定
透かしの耐久性
連合学習

Theoretically Principled Trade-off for Stateful Defenses against Query-Based Black-Box Attacks

Authors: Ashish Hooda, Neal Mangaokar, Ryan Feng, Kassem Fawaz, Somesh Jha, Atul Prakash | Published: 2023-07-30
サイバーセキュリティ
敵対的スペクトル攻撃検出
透かしの耐久性

A LLM Assisted Exploitation of AI-Guardian

Authors: Nicholas Carlini | Published: 2023-07-20
プロンプトインジェクション
メンバーシップ推論
透かしの耐久性

MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots

Authors: Gelei Deng, Yi Liu, Yuekang Li, Kailong Wang, Ying Zhang, Zefeng Li, Haoyu Wang, Tianwei Zhang, Yang Liu | Published: 2023-07-16 | Updated: 2023-10-25
データ漏洩
プロンプトインジェクション
透かしの耐久性

An Algorithm for Persistent Homology Computation Using Homomorphic Encryption

Authors: Dominic Gold, Koray Karabina, Francis C. Motta | Published: 2023-07-04
アルゴリズム設計
計算複雑性
透かしの耐久性

When Vision Fails: Text Attacks Against ViT and OCR

Authors: Nicholas Boucher, Jenny Blessing, Ilia Shumailov, Ross Anderson, Nicolas Papernot | Published: 2023-06-12
性能評価
攻撃パターン抽出
透かしの耐久性

Customized Watermarking for Deep Neural Networks via Label Distribution Perturbation

Authors: Tzu-Yun Chien, Chih-Ya Shen | Published: 2022-08-10
カスタマイズ手法
敵対的サンプル
透かしの耐久性

Subsequent embedding in targeted image steganalysis: Theoretical framework and practical applications

Authors: David Megías, Daniel Lerch-Hostalot | Published: 2021-07-29 | Updated: 2022-03-15
アルゴリズム
実験的検証
透かしの耐久性

Defending against adversarial attacks by randomized diversification

Authors: Olga Taran, Shideh Rezaeifar, Taras Holotyak, Slava Voloshynovskiy | Published: 2019-04-01
敵対的サンプルの検知
敵対的攻撃検出
透かしの耐久性