敵対的学習

GIFDL: Generated Image Fluctuation Distortion Learning for Enhancing Steganographic Security

Authors: Xiangkun Wang, Kejiang Chen, Yuang Qi, Ruiheng Liu, Weiming Zhang, Nenghai Yu | Published: 2025-04-21
敵対的学習
生成モデル
透かし技術

Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent

Authors: Philip Doldo, Derek Everett, Amol Khanna, Andre T Nguyen, Edward Raff | Published: 2025-03-25
敵対的サンプルの脆弱性
敵対的学習
深層ネットワークの堅牢性

TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributions

Authors: Wang YuHang, Junkang Guo, Aolei Liu, Kaihao Wang, Zaitong Wu, Zhenyu Liu, Wenfei Yin, Jian Liu | Published: 2025-03-02 | Updated: 2025-03-21
ロバスト性
敵対的学習
敵対的訓練

SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage

Authors: Xiaoning Dong, Wenbo Hu, Wei Xu, Tianxing He | Published: 2024-12-19 | Updated: 2025-03-21
プロンプトインジェクション
大規模言語モデル
敵対的学習

Protecting Confidentiality, Privacy and Integrity in Collaborative Learning

Authors: Dong Chen, Alice Dethise, Istemi Ekin Akkus, Ivica Rimac, Klaus Satzke, Antti Koskela, Marco Canini, Wei Wang, Ruichuan Chen | Published: 2024-12-11 | Updated: 2025-04-17
プライバシー保護フレームワーク
差分プライバシー
敵対的学習

Robust LLM safeguarding via refusal feature adversarial training

Authors: Lei Yu, Virginie Do, Karen Hambardzumyan, Nicola Cancedda | Published: 2024-09-30 | Updated: 2025-03-20
プロンプトインジェクション
モデルの堅牢性
敵対的学習

LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples

Authors: Jia-Yu Yao, Kun-Peng Ning, Zhen-Hui Liu, Mu-Nan Ning, Yu-Yang Liu, Li Yuan | Published: 2023-10-02 | Updated: 2024-08-04
ハルシネーション
敵対的サンプルの脆弱性
敵対的学習

Statistical Detection of Adversarial examples in Blockchain-based Federated Forest In-vehicle Network Intrusion Detection Systems

Authors: Ibrahim Aliyu, Selinde van Engelenburg, Muhammed Bashir Muazu, Jinsul Kim, Chang Gyoon Lim | Published: 2022-07-11
ポイズニング
攻撃タイプ
敵対的学習

Wild Networks: Exposure of 5G Network Infrastructures to Adversarial Examples

Authors: Giovanni Apruzzese, Rodion Vladimirov, Aliya Tastemirova, Pavel Laskov | Published: 2022-07-04
ネットワークスライシング
リスク評価手法
敵対的学習

IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound

Authors: Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham, M. Pawan Kumar, Robert Stanforth | Published: 2022-06-29 | Updated: 2023-05-31
アルゴリズム設計
効率的証明システム
敵対的学習