Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales
Search
Open menu
Home
Papers
2101.05930
Cited By
v1
v2 (latest)
Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
International Conference on Learning Representations (ICLR), 2021
15 January 2021
Yige Li
Lingjuan Lyu
Nodens Koren
X. Lyu
Yue Liu
Jiabo He
AAML
FedML
Re-assign community
ArXiv (abs)
PDF
HTML
Github (122★)
Papers citing
"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks"
50 / 283 papers shown
Backdoor Attacks against Voice Recognition Systems: A Survey
ACM Computing Surveys (ACM Comput. Surv.), 2023
Baochen Yan
Jiahe Lan
Zheng Yan
AAML
198
18
0
23 Jul 2023
Adversarial Feature Map Pruning for Backdoor
International Conference on Learning Representations (ICLR), 2023
Dong Huang
Qingwen Bu
AAML
181
5
0
21 Jul 2023
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
Neural Information Processing Systems (NeurIPS), 2023
Shaokui Wei
Ruotong Wang
H. Zha
Baoyuan Wu
TPM
212
45
0
20 Jul 2023
Co(ve)rtex: ML Models as storage channels and their (mis-)applications
Md Abdullah Al Mamun
Quazi Mishkatul Alam
Erfan Shayegani
Pedram Zaree
Ihsen Alouani
Nael B. Abu-Ghazaleh
269
0
0
17 Jul 2023
Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
Zihao Zhu
Ruotong Wang
Shaokui Wei
Li Shen
Yanbo Fan
Baoyuan Wu
AAML
SILM
322
11
0
14 Jul 2023
A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives
AAAI Conference on Artificial Intelligence (AAAI), 2023
Yudong Gao
Honglong Chen
Yang Liu
Junjian Li
Anqing Zhang
Zhibo Wang
AAML
143
24
0
03 Jul 2023
Efficient Backdoor Removal Through Natural Gradient Fine-tuning
Nazmul Karim
Abdullah Al Arafat
Umar Khalid
Zhishan Guo
Naznin Rahnavard
AAML
155
1
0
30 Jun 2023
Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features
Neural Information Processing Systems (NeurIPS), 2023
Mingli Zhu
Shaokui Wei
H. Zha
Baoyuan Wu
AAML
190
50
0
29 Jun 2023
A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2023
Wandi Qiao
Hong Sun
Pengfei Xia
Beihao Xia
Xue Rui
Wei Zhang
Qinglang Guo
Bin Li
AAML
281
11
0
14 Jun 2023
DHBE: Data-free Holistic Backdoor Erasing in Deep Neural Networks via Restricted Adversarial Distillation
ACM Asia Conference on Computer and Communications Security (AsiaCCS), 2023
Zhicong Yan
Shenghong Li
Ruijie Zhao
Yuan Tian
Yuanyuan Zhao
AAML
160
13
0
13 Jun 2023
TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models
Neural Information Processing Systems (NeurIPS), 2023
Jiaqi Xue
Mengxin Zheng
Ting Hua
Yilin Shen
Ye Liu
Ladislau Bölöni
Qian Lou
433
46
0
12 Jun 2023
Revisiting Data-Free Knowledge Distillation with Poisoned Teachers
International Conference on Machine Learning (ICML), 2023
Junyuan Hong
Yi Zeng
Shuyang Yu
Lingjuan Lyu
R. Jia
Jiayu Zhou
AAML
115
15
0
04 Jun 2023
Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers
Ke Xu
Hongrui Chen
Zihao Zhu
Li Liu
Baoyuan Wu
DiffM
380
13
0
01 Jun 2023
UMD: Unsupervised Model Detection for X2X Backdoor Attacks
International Conference on Machine Learning (ICML), 2023
Zhen Xiang
Zidi Xiong
Yue Liu
AAML
369
27
0
29 May 2023
Robust Natural Language Understanding with Residual Attention Debiasing
Annual Meeting of the Association for Computational Linguistics (ACL), 2023
Fei Wang
James Y. Huang
Tianyi Yan
Wenxuan Zhou
Muhao Chen
161
13
0
28 May 2023
From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
North American Chapter of the Association for Computational Linguistics (NAACL), 2023
Qin Liu
Fei Wang
Chaowei Xiao
Muhao Chen
AAML
273
29
0
24 May 2023
Reconstructive Neuron Pruning for Backdoor Defense
International Conference on Machine Learning (ICML), 2023
Yige Li
X. Lyu
Jiabo He
Nodens Koren
Lingjuan Lyu
Yue Liu
Yugang Jiang
AAML
272
64
0
24 May 2023
Towards Generalizable Data Protection With Transferable Unlearnable Examples
Bin Fang
Yue Liu
Shuang Wu
Tianyi Zheng
Shouhong Ding
Ran Yi
Lizhuang Ma
177
6
0
18 May 2023
Re-thinking Data Availablity Attacks Against Deep Neural Networks
Bin Fang
Yue Liu
Shuang Wu
Ran Yi
Shouhong Ding
Lizhuang Ma
AAML
174
0
0
18 May 2023
Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023
T. Shaik
Xiaohui Tao
Haoran Xie
Lin Li
Xiaofeng Zhu
Qingyuan Li
MU
516
51
0
10 May 2023
Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias
Annual Meeting of the Association for Computational Linguistics (ACL), 2023
Zhiyuan Zhang
Deli Chen
Hao Zhou
Fandong Meng
Jie Zhou
Xu Sun
179
9
0
08 May 2023
Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks
Nils Lukas
Florian Kerschbaum
267
1
0
07 May 2023
Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization
IEEE International Conference on Computer Vision (ICCV), 2023
Mingli Zhu
Shaokui Wei
Li Shen
Yanbo Fan
Baoyuan Wu
AAML
204
77
0
24 Apr 2023
UNICORN: A Unified Backdoor Trigger Inversion Framework
International Conference on Learning Representations (ICLR), 2023
Zhenting Wang
Kai Mei
Juan Zhai
Shiqing Ma
LLMSV
199
58
0
05 Apr 2023
Detecting Backdoors in Pre-trained Encoders
Computer Vision and Pattern Recognition (CVPR), 2023
Shiwei Feng
Guanhong Tao
Shuyang Cheng
Guangyu Shen
Xiangzhe Xu
Yingqi Liu
Kaiyuan Zhang
Shiqing Ma
Xiangyu Zhang
244
73
0
23 Mar 2023
Backdoor Defense via Adaptively Splitting Poisoned Dataset
Computer Vision and Pattern Recognition (CVPR), 2023
Kuofeng Gao
Yang Bai
Jindong Gu
Yong-Liang Yang
Shutao Xia
AAML
175
69
0
23 Mar 2023
Influencer Backdoor Attack on Semantic Segmentation
International Conference on Learning Representations (ICLR), 2023
Haoheng Lan
Jindong Gu
Juil Sock
Hengshuang Zhao
AAML
320
9
0
21 Mar 2023
AdaptGuard: Defending Against Universal Attacks for Model Adaptation
Lijun Sheng
Jian Liang
Ran He
Zilei Wang
Tien-Ping Tan
AAML
256
6
0
19 Mar 2023
Backdoor Defense via Deconfounded Representation Learning
Computer Vision and Pattern Recognition (CVPR), 2023
Zaixin Zhang
Qi Liu
Zhicai Wang
Zepu Lu
Qingyong Hu
AAML
139
47
0
13 Mar 2023
CUDA: Convolution-based Unlearnable Datasets
Computer Vision and Pattern Recognition (CVPR), 2023
Vinu Sankar Sadasivan
Mahdi Soltanolkotabi
Soheil Feizi
MU
235
29
0
07 Mar 2023
CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning
IEEE International Conference on Computer Vision (ICCV), 2023
Hritik Bansal
Nishad Singhi
Yu Yang
Fan Yin
Aditya Grover
Kai-Wei Chang
AAML
372
66
0
06 Mar 2023
Aegis: Mitigating Targeted Bit-flip Attacks against Deep Neural Networks
USENIX Security Symposium (USENIX Security), 2023
Jialai Wang
Ziyuan Zhang
Meiqi Wang
Han Qiu
Tianwei Zhang
Qi Li
Zongpeng Li
Tao Wei
Chao Zhang
AAML
211
34
0
27 Feb 2023
SATBA: An Invisible Backdoor Attack Based On Spatial Attention
International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), 2023
Huasong Zhou
Xiaowei Xu
Zhenyu Wang
Leon Bevan Bullock
AAML
183
2
0
25 Feb 2023
Defending Against Backdoor Attacks by Layer-wise Feature Analysis
Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2023
N. Jebreel
J. Domingo-Ferrer
Yiming Li
AAML
224
21
0
24 Feb 2023
Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions
Marwan Omar
SILM
AAML
199
21
0
14 Feb 2023
Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data
Network and Distributed System Security Symposium (NDSS), 2023
Gorka Abad
Oguzhan Ersoy
S. Picek
A. Urbieta
AAML
175
26
0
13 Feb 2023
SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency
International Conference on Learning Representations (ICLR), 2023
Junfeng Guo
Yiming Li
Hang Zhang
Hanqing Guo
Lichao Sun
Cong Liu
AAML
MLAU
206
134
0
07 Feb 2023
Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks
Knowledge Discovery and Data Mining (KDD), 2023
Zeyu Qin
Liuyi Yao
Daoyuan Chen
Yaliang Li
Bolin Ding
Minhao Cheng
FedML
367
32
0
03 Feb 2023
BackdoorBox: A Python Toolbox for Backdoor Learning
Yiming Li
Mengxi Ya
Yang Bai
Yong Jiang
Shutao Xia
AAML
218
49
0
01 Feb 2023
Salient Conditional Diffusion for Defending Against Backdoor Attacks
Brandon B. May
N. Joseph Tatro
Dylan Walker
Piyush Kumar
N. Shnidman
DiffM
204
10
0
31 Jan 2023
Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
Network and Distributed System Security Symposium (NDSS), 2023
Rui Zhu
Di Tang
Siyuan Tang
Guanhong Tao
Shiqing Ma
Luyi Xing
Haixu Tang
DD
190
6
0
29 Jan 2023
Distilling Cognitive Backdoor Patterns within an Image
International Conference on Learning Representations (ICLR), 2023
Hanxun Huang
Jiabo He
S. Erfani
James Bailey
AAML
420
33
0
26 Jan 2023
Towards Understanding How Self-training Tolerates Data Backdoor Poisoning
Soumyadeep Pal
Ren Wang
Yuguang Yao
Sijia Liu
199
7
0
20 Jan 2023
On the Vulnerability of Backdoor Defenses for Federated Learning
AAAI Conference on Artificial Intelligence (AAAI), 2023
Pei Fang
Jinghui Chen
FedML
180
56
0
19 Jan 2023
Dataset Distillation: A Comprehensive Review
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
Ruonan Yu
Songhua Liu
Xinchao Wang
DD
354
168
0
17 Jan 2023
BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense
Network and Distributed System Security Symposium (NDSS), 2023
Shuyang Cheng
Guanhong Tao
Yingqi Liu
Shengwei An
Xiangzhe Xu
...
Guangyu Shen
Kaiyuan Zhang
Qiuling Xu
Shiqing Ma
Xiangyu Zhang
AAML
214
20
0
16 Jan 2023
Backdoor Attacks Against Dataset Distillation
Network and Distributed System Security Symposium (NDSS), 2023
Yugeng Liu
Zheng Li
Michael Backes
Yun Shen
Yang Zhang
DD
239
33
0
03 Jan 2023
Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition
Hasan Hammoud
Shuming Liu
Mohammad Alkhrashi
Fahad Albalawi
Guohao Li
AAML
274
12
0
03 Jan 2023
Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing
IEEE Conference on Computer Communications (INFOCOM), 2022
Tian Dong
Ziyuan Zhang
Han Qiu
Tianwei Zhang
Hewu Li
T. Wang
AAML
258
10
0
22 Dec 2022
Fine-Tuning Is All You Need to Mitigate Backdoor Attacks
Zeyang Sha
Xinlei He
Pascal Berrang
Mathias Humbert
Yang Zhang
AAML
260
49
0
18 Dec 2022
Previous
1
2
3
4
5
6
Next
