-
DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks in the Physical WorldCaixin Kang, Yinpeng Dong, Zhengyi Wang, Shouwei Ruan, Hang Su, Xingxing WeiarXiv 2023. Paper  2023-06-152023-06-15
-
An Efficient Membership Inference Attack for the Diffusion Model by Proximal InitializationFei Kong, Jinhao Duan, RuiPeng Ma, Hengtao Shen, Xiaofeng Zhu, Xiaoshuang Shi, Kaidi XuarXiv 2023. Paper  2023-05-262023-05-26
-
Differentially Private Latent Diffusion ModelsSaiyue Lyu, Margarita Vinaroz, Michael F. Liu, Mijung ParkarXiv 2023. Paper  2023-05-252023-05-25
-
Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and ControllabilityHaotian Xue, Alexandre Araujo, Bin Hu, Yongxin Chen2023-05-252023-05-25
-
Latent Magic: An Investigation into Adversarial Examples Crafted in the Semantic Latent SpaceBoYang ZhengarXiv 2023. Paper  2023-05-222023-05-22
-
Mist: Towards Improved Adversarial Examples for Diffusion ModelsChumeng Liang, Xiaoyu WuarXiv 2023. Paper  2023-05-222023-05-22
-
Zero-Day Backdoor Attack against Text-to-Image Diffusion Models via PersonalizationYihao Huang, Qing Guo, Felix Juefei-XuarXiv 2023. Paper  2023-05-182023-05-18
-
Content-based Unrestricted Adversarial AttackZhaoyu Chen, Bo Li, Shuang Wu, Kaixun Jiang, Shouhong Ding, Wenqiang ZhangarXiv 2023. Paper  2023-05-182023-05-18
-
Raising the Bar for Certified Adversarial Robustness with Diffusion ModelsThomas Altstidl, David Dobre, Björn Eskofier, Gauthier Gidel, Leo SchwinnarXiv 2023. Paper  2023-05-172023-05-17
-
On enhancing the robustness of Vision Transformers: Defensive DiffusionRaza Imam, Muhammad Huzaifa, Mohammed El-Amine Azz2023-05-142023-05-14
-
Diffusion Models for Imperceptible and Transferable Adversarial AttackJianqi Chen, Hao Chen, Keyan Chen, Yilan Zhang, Zhengxia Zou, Zhenwei Shi2023-05-142023-05-14
-
Generative Steganography DiffusionPing Wei, Qing Zhou, Zichi Wang, Zhenxing Qian, Xinpeng Zhang, Sheng LiarXiv 2023. Paper  2023-05-052023-05-05
-
A Pilot Study of Query-Free Adversarial Attack against Stable DiffusionHaomin Zhuang, Yihua Zhang, Sijia LiuCVPR Workshop 2023. Paper  2023-04-032023-04-03
-
Black-box Backdoor Defense via Zero-shot Image PurificationYucheng Shi, Mengnan Du, Xuansheng Wu, Zihan Guan, Ninghao LiuarXiv 2023. Paper  2023-03-212023-03-21
-
Adversarial Counterfactual Visual ExplanationsGuillaume Jeanneret, Loïc Simon, Frédéric Jurie2023-03-172023-03-17
-
Robust Evaluation of Diffusion-Based Adversarial PurificationMinjong Lee, Dongwoo KimICLR 2023. Paper  2023-03-162023-03-16
-
The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion ModelsHadi M. Dolatabadi, Sarah Erfani, Christopher LeckiearXiv 2023. Paper  2023-03-152023-03-15
-
TrojDiff: Trojan Attacks on Diffusion Models with Diverse TargetsWeixin Chen, Dawn Song, Bo Li2023-03-102023-03-10
-
Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep LearningAprilPyone MaungMaung, Hitoshi KiyaarXiv 2023. Paper  2023-03-092023-03-09
-
Differentially Private Diffusion Models Generate Useful Synthetic ImagesSahra Ghalebikesabi, Leonard Berrada, Sven Gowal, Ira Ktena, Robert Stanforth, Jamie Hayes, Soham De, Samuel L. Smith, Olivia Wiles, Borja BallearXiv 2023. Paper  2023-02-272023-02-27
-
Data Forensics in Diffusion Models: A Systematic Analysis of Membership PrivacyDerui Zhu, Dingfan Chen, Jens Grossklags, Mario FritzarXiv 2023. Paper  2023-02-152023-02-15
-
Raising the Cost of Malicious AI-Powered Image EditingHadi Salman, Alaa Khaddaj, Guillaume Leclerc, Andrew Ilyas, Aleksander Madry2023-02-132023-02-13
-
Better Diffusion Models Further Improve Adversarial TrainingZekai Wang, Tianyu Pang, Chao Du, Min Lin, Weiwei Liu, Shuicheng Yan2023-02-092023-02-09
-
Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial ExamplesChumeng Liang, Xiaoyu Wu, Yang Hua, Jiaru Zhang, Yiming Xue, Tao Song, Zhengui Xue, Ruhui Ma, Haibing GuanarXiv 2023. Paper  2023-02-092023-02-09
-
Membership Inference Attacks against Diffusion ModelsTomoya Matsumoto, Takayuki Miura, Naoto YanaiarXiv 2023. Paper  2023-02-072023-02-07
-
MorDIFF: Recognition Vulnerability and Attack Detectability of Face Morphing Attacks Created by Diffusion AutoencodersNaser Damer, Meiling Fang, Patrick Siebke, Jan Niklas Kolf, Marco Huber, Fadi Boutros2023-02-032023-02-03
-
Are Diffusion Models Vulnerable to Membership Inference Attacks?Jinhao Duan, Fei Kong, Shiqi Wang, Xiaoshuang Shi, Kaidi XuarXiv 2023. Paper  2023-02-022023-02-02
-
Extracting Training Data from Diffusion ModelsNicholas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash Sehwag, Florian Tramèr, Borja Balle, Daphne Ippolito, Eric WallacearXiv 2023. Paper  2023-02-022023-02-02
-
Salient Conditional Diffusion for Defending Against Backdoor AttacksBrandon B. May, N. Joseph Tatro, Piyush Kumar, Nathan ShnidmanICLR Workshop 2023. Paper  2023-01-312023-01-31
-
Extracting Training Data from Diffusion ModelsNicholas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash Sehwag, Florian Tramèr, Borja Balle, Daphne Ippolito, Eric WallacearXiv 2023. Paper  2023-01-302023-01-30
-
2023-01-24
-
Denoising Diffusion Probabilistic Models as a Defense against Adversarial AttacksLars Lien Ankile, Anna Midgley, Sebastian Weisshaar2023-01-172023-01-17
-
DensePure: Understanding Diffusion Models towards Adversarial RobustnessChaowei Xiao, Zhongzhu Chen, Kun Jin, Jiongxiao Wang, Weili Nie, Mingyan Liu, Anima Anandkumar, Bo Li, Dawn SongNeurIPS 2022. Paper  2022-11-012022-11-01
-
Differentially Private Diffusion ModelsTim Dockhorn, Tianshi Cao, Arash Vahdat, Karsten Kreis2022-10-182022-10-18
-
Improving Adversarial Robustness by Contrastive Guided Diffusion ProcessYidong Ouyang, Liyan Xie, Guang ChengarXiv 2022. Paper  2022-10-182022-10-18
-
Fight Fire With Fire: Reversing Skin Adversarial Examples by Multiscale Diffusive and Denoising Aggregation MechanismYongwei Wang, Yuan Li, Zhiqi ShenarXiv 2022. Paper  2022-08-222022-08-22
-
PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud RecognitionJiachen Sun, Weili Nie, Zhiding Yu, Z. Morley Mao, Chaowei XiaoarXiv 2022. Paper  2022-08-212022-08-21
-
Threat Model-Agnostic Adversarial Defense using Diffusion ModelsTsachi Blau, Roy Ganz, Bahjat Kawar, Alex Bronstein, Michael Elad2022-07-172022-07-17
-
Back to the Source: Diffusion-Driven Test-Time AdaptationJin Gao, Jialing Zhang, Xihui Liu, Trevor Darrell, Evan Shelhamer, Dequan Wang2022-07-072022-07-07
-
(Certified!!) Adversarial Robustness for Free!Nicholas Carlini, Florian Tramer, Krishnamurthy (Dj)Dvijotham, J. Zico KolterICLR 2023. Paper  2022-06-212022-06-21
-
Guided Diffusion Model for Adversarial Purification from Random NoiseQuanlin Wu, Hang Ye, Yuntian GuarXiv 2022. Paper  2022-06-172022-06-17
-
Guided Diffusion Model for Adversarial PurificationJinyi Wang, Zhaoyang Lyu, Dahua Lin, Bo Dai, Hongfei Fu2022-05-302022-05-30
-
Diffusion Models for Adversarial PurificationWeili Nie, Brandon Guo, Yujia Huang, Chaowei Xiao, Arash Vahdat, Anima Anandkumar2022-05-162022-05-16
-
TFDPM: Attack detection for cyber-physical systems with diffusion probabilistic modelsTijin Yan, Tong Zhou, Yufeng Zhan, Yuanqing XiaElsveier Knowledge-Based Systems 2021. Paper  2021-12-202021-12-20
-
Adversarial purification with Score-based generative modelsJongmin Yoon, Sung Ju Hwang, Juho Lee2021-06-112021-06-11
Counts - 45   Back to
top