LTD: Low Temperature Distillation for Gradient Masking-free Adversarial Training

v1v2v3v4 (latest)

LTD: Low Temperature Distillation for Gradient Masking-free Adversarial Training

ACM Transactions on Cyber-Physical Systems (ACM TCPS), 2021

3 November 2021

ArXiv (abs)PDF HTML HuggingFace (1 upvotes)

Papers citing "LTD: Low Temperature Distillation for Gradient Masking-free Adversarial Training"

19 / 19 papers shown

Title
Revisiting the Relationship between Adversarial and Clean Training: Why Clean Training Can Make Adversarial Training Better MingWei Zhou Xiaobing Pei AAML 822 0 0 30 Mar 2025
LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial Attacks Joana Cabral Costa Tiago Roxo Hugo Manuel Proença Pedro R. M. Inácio AAML 235 1 0 27 Feb 2025
Democratic Training Against Universal Adversarial PerturbationsInternational Conference on Learning Representations (ICLR), 2025 Bing-Jie Sun Jun Sun Wei Zhao AAML 210 0 0 08 Feb 2025
Dynamic Guidance Adversarial Distillation with Enhanced Teacher KnowledgeEuropean Conference on Computer Vision (ECCV), 2024 Hyejin Park Dongbo Min AAML 161 8 0 03 Sep 2024
Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness Erh-Chung Chen Pin-Yu Chen I-Hsin Chung Che-Rung Lee 214 5 0 28 Jun 2024
On adversarial training and the 1 Nearest Neighbor classifier Amir Hagai Yair Weiss AAML 192 0 0 09 Apr 2024
Machine Learning Robustness: A Primer Houssem Ben Braiek Foutse Khomh AAML OOD 351 20 0 01 Apr 2024
Indirect Gradient Matching for Adversarial Robust DistillationInternational Conference on Learning Representations (ICLR), 2023 Hongsin Lee Yujin Yang Changick Kim AAML FedML 216 3 0 06 Dec 2023
Topology-Preserving Adversarial Training Xiaoyue Mi Fan Tang Yepeng Weng Danding Wang Juan Cao Sheng Tang Peng Li Yang Liu 218 1 0 29 Nov 2023
IRAD: Implicit Representation-driven Image Resampling against Adversarial AttacksInternational Conference on Learning Representations (ICLR), 2023 Yue Cao Tianlin Li Xiaofeng Cao Ivor Tsang Yang Liu Qing Guo AAML 197 4 0 18 Oct 2023
Revisiting and Advancing Adversarial Training Through A Simple Baseline Hong Liu AAML 158 0 0 13 Jun 2023
Annealing Self-Distillation Rectification Improves Adversarial TrainingInternational Conference on Learning Representations (ICLR), 2023 Yuehua Wu Hung-Jui Wang Shang-Tse Chen AAML 233 6 0 20 May 2023
How Deep Learning Sees the World: A Survey on Adversarial Attacks & DefensesIEEE Access (IEEE Access), 2023 Joana Cabral Costa Tiago Roxo Hugo Manuel Proença Pedro R. M. Inácio AAML 318 103 0 18 May 2023
Overload: Latency Attacks on Object Detection for Edge DevicesComputer Vision and Pattern Recognition (CVPR), 2023 Erh-Chung Chen Pin-Yu Chen I-Hsin Chung Che-Rung Lee AAML 266 19 0 11 Apr 2023
Denoising Autoencoder-based Defensive Distillation as an Adversarial Robustness AlgorithmACM SIGAda Ada Letters (Ada Lett.), 2023 Bakary Badjie José Cecílio António Casimiro AAML 129 5 0 28 Mar 2023
DISCO: Adversarial Defense with Local Implicit FunctionsNeural Information Processing Systems (NeurIPS), 2022 Chih-Hui Ho Nuno Vasconcelos AAML 349 51 0 11 Dec 2022
Robust Models are less Over-ConfidentNeural Information Processing Systems (NeurIPS), 2022 Julia Grabinski Paul Gavrikov J. Keuper Margret Keuper AAML 200 28 0 12 Oct 2022
Diversified Adversarial Attacks based on Conjugate Gradient MethodInternational Conference on Machine Learning (ICML), 2022 Keiichiro Yamamura Haruki Sato Nariaki Tateiwa Nozomi Hata Toru Mitsutake Issa Oe Hiroki Ishikura Katsuki Fujisawa AAML 192 15 0 20 Jun 2022
Adversarial Robustness through the Lens of Convolutional Filters Paul Gavrikov J. Keuper 135 15 0 05 Apr 2022