v1v2 (latest)

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks

International Conference on Learning Representations (ICLR), 2021

15 January 2021

ArXiv (abs)PDF HTML Github (122★)

Papers citing "Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks"

50 / 281 papers shown

Title
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency Soumyadeep Pal Yuguang Yao Ren Wang Bingquan Shen Sijia Liu AAML 192 13 0 15 Mar 2024
On the Effectiveness of Distillation in Mitigating Backdoors in Pre-trained Encoder Tingxu Han Shenghan Huang Ziqi Ding Weisong Sun Yebo Feng ... Hanwei Qian Cong Wu Quanjun Zhang Yang Liu Zhenyu Chen 146 10 0 06 Mar 2024
A general approach to enhance the survivability of backdoor attacks by decision path coupling Yufei Zhao Dingji Wang Bihuan Chen Ziqian Chen Xin Peng AAML 186 0 0 05 Mar 2024
Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm Yanqi Qiao Dazhuang Liu Rui Wang Kaitai Liang AAML 214 1 0 23 Feb 2024
Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection Jiawei Liang Yaning Tan Aishan Liu Yang Liu Junhao Kuang Xiaochun Cao AAML 163 31 0 18 Feb 2024
Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors D. Sahabandu Xiaojun Xu Arezoo Rajabi Luyao Niu Bhaskar Ramasubramanian Bo Li Radha Poovendran AAML 168 1 0 12 Feb 2024
Architectural Neural Backdoors from First PrinciplesIEEE Symposium on Security and Privacy (S&P), 2024 Harry Langford Ilia Shumailov Yiren Zhao Robert D. Mullins Nicolas Papernot AAML 202 9 0 10 Feb 2024
Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor AttacksIEEE Transactions on Dependable and Secure Computing (IEEE TDSC), 2024 Yige Li Jiabo He Jiabo He Hanxun Huang Xingjun Ma Yu-Gang Jiang AAML 240 3 0 27 Jan 2024
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor LearningInternational Journal of Computer Vision (IJCV), 2024 Baoyuan Wu Hongrui Chen Ruotong Wang Zihao Zhu Shaokui Wei Danni Yuan Mingli Zhu Ke Xu Li Liu Chaoxiao Shen AAML ELM 247 16 0 26 Jan 2024
Decentralized Federated Learning: A Survey on Security and PrivacyIEEE Transactions on Big Data (IEEE Trans. Big Data), 2024 Ehsan Hallaji R. Razavi-Far R. Razavi-Far Boyu Wang Qiang Yang FedML 232 80 0 25 Jan 2024
WPDA: Frequency-based Backdoor Attack with Wavelet Packet DecompositionNeural Networks (NN), 2024 Zhengyao Song Yongqiang Li Danni Yuan Li Liu Shaokui Wei Baoyuan Wu AAML 265 4 0 24 Jan 2024
BadChain: Backdoor Chain-of-Thought Prompting for Large Language ModelsInternational Conference on Learning Representations (ICLR), 2024 Zhen Xiang Fengqing Jiang Zidi Xiong Bhaskar Ramasubramanian Radha Poovendran Bo Li LRM SILM 241 77 0 20 Jan 2024
Hijacking Attacks against Neural Networks by Analyzing Training Data Yunjie Ge Qian Wang Huayang Huang Qi Li Cong Wang Chao Shen Lingchen Zhao Peipei Jiang Zheng Fang Shenyi Zhang 189 0 0 18 Jan 2024
End-to-End Anti-Backdoor Learning on Images and Time Series Yujing Jiang Jiabo He S. Erfani Yige Li James Bailey 185 1 0 06 Jan 2024
PosCUDA: Position based Convolution for Unlearnable Audio Datasets V. Gokul Shlomo Dubnov SSL 173 4 0 04 Jan 2024
Pre-trained Trojan Attacks for Visual Recognition Aishan Liu Xinwei Zhang Yisong Xiao Yuguang Zhou Yaning Tan Jinyang Guo Xianglong Liu Xiaochun Cao Dacheng Tao AAML 222 39 0 23 Dec 2023
UltraClean: A Simple Framework to Train Robust Neural Networks against Backdoor Attacks Bingyin Zhao Yingjie Lao AAML 281 2 0 17 Dec 2023
TrojFair: Trojan Fairness Attacks Meng Zheng Jiaqi Xue Yi Sheng Lei Yang Qian Lou Lei Jiang 181 4 0 16 Dec 2023
Defenses in Adversarial Machine Learning: A Survey Baoyuan Wu Shaokui Wei Mingli Zhu Meixi Zheng Zihao Zhu Ruotong Wang Hongrui Chen Danni Yuan Li Liu Qingshan Liu AAML 286 21 0 13 Dec 2023
Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models Sze Jue Yang Chinh D. La Quang H. Nguyen Kok-Seng Wong Anh Tran Chee Seng Chan Khoa D. Doan AAML 169 1 0 06 Dec 2023
Towards Sample-specific Backdoor Attack with Clean Labels via Attribute TriggerIEEE Transactions on Dependable and Secure Computing (IEEE TDSC), 2023 Yiming Li Mingyan Zhu Junfeng Guo Tao Wei Shu-Tao Xia Zhan Qin AAML 316 5 0 03 Dec 2023
Universal Backdoor AttacksInternational Conference on Learning Representations (ICLR), 2023 Benjamin Schneider Nils Lukas Florian Kerschbaum SILM 226 7 0 30 Nov 2023
Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method PerspectiveInternational Conference on Learning Representations (ICLR), 2023 Ming-Yu Chung Sheng-Yen Chou Chia-Mu Yu Pin-Yu Chen Sy-Yen Kuo Tsung-Yi Ho DD 374 9 0 28 Nov 2023
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution ShiftAAAI Conference on Artificial Intelligence (AAAI), 2023 Shengwei An Sheng-Yen Chou Kaiyuan Zhang Qiuling Xu Guanhong Tao ... Shuyang Cheng Shiqing Ma Pin-Yu Chen Tsung-Yi Ho Xiangyu Zhang DiffM AAML 370 37 0 27 Nov 2023
A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective Xianghua Xie Chen Hu Hanchi Ren Jingjing Deng FedML AAML 265 32 0 27 Nov 2023
Mitigating Backdoors within Deep Neural Networks in Data-limited Configuration Soroush Hashemifar Saeed Parsa Morteza Zakeri-Nasrabadi AAML 156 0 0 13 Nov 2023
Label Poisoning is All You NeedNeural Information Processing Systems (NeurIPS), 2023 Rishi Jha J. Hayase Sewoong Oh AAML 227 42 0 29 Oct 2023
CBD: A Certified Backdoor Detector Based on Local Dominant ProbabilityNeural Information Processing Systems (NeurIPS), 2023 Zhen Xiang Zidi Xiong Bo Li AAML 285 19 0 26 Oct 2023
On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts Yixin Wu Ning Yu Michael Backes Yun Shen Yang Zhang DiffM 290 11 0 25 Oct 2023
FLTracer: Accurate Poisoning Attack Provenance in Federated Learning Xinyu Zhang Qingyu Liu Zhongjie Ba Yuan Hong Tianhang Zheng Feng Lin Liwang Lu Kui Ren AAML 203 18 0 20 Oct 2023
Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data Lukas Struppek Martin Hentschel Clifton A. Poth Dominik Hintersdorf Kristian Kersting SILM DiffM 168 5 0 10 Oct 2023
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade DefenseConference on Computer and Communications Security (CCS), 2023 Hua Ma Shang Wang Yansong Gao Zhi-Li Zhang Huming Qiu Minhui Xue A. Abuadbba Anmin Fu Surya Nepal Derek Abbott AAML 245 12 0 01 Oct 2023
Post-Training Overfitting Mitigation in DNN Classifiers Hang Wang David J. Miller G. Kesidis AAML 115 0 0 28 Sep 2023
SPFL: A Self-purified Federated Learning Method Against Poisoning AttacksIEEE Transactions on Information Forensics and Security (IEEE TIFS), 2023 Zizhen Liu Weiyang He Chip-Hong Chang Jing Ye Huawei Li Xiaowei Li 198 10 0 19 Sep 2023
Physical Invisible Backdoor Based on Camera ImagingACM Multimedia (ACM MM), 2023 Yusheng Guo Nan Zhong Zhenxing Qian Xinpeng Zhang DiffM 185 3 0 14 Sep 2023
Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security ReviewIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023 Pengzhou Cheng Zongru Wu Wei Du Haodong Zhao Wei Lu Gongshen Liu SILM AAML 637 44 0 12 Sep 2023
Towards Robust Model Watermark via Reducing Parametric VulnerabilityIEEE International Conference on Computer Vision (ICCV), 2023 Guanhao Gan Yiming Li Dongxian Wu Shu-Tao Xia AAML 163 18 0 09 Sep 2023
LMSanitator: Defending Prompt-Tuning Against Task-Agnostic BackdoorsNetwork and Distributed System Security Symposium (NDSS), 2023 Chengkun Wei Wenlong Meng Zhikun Zhang M. Chen Ming-Hui Zhao Wenjing Fang Lei Wang Zihui Zhang Wenzhi Chen AAML 149 14 0 26 Aug 2023
BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input DetectionInternational Conference on Learning Representations (ICLR), 2023 Tinghao Xie Xiangyu Qi Ping He Yiming Li Jiachen T. Wang Prateek Mittal AAML 180 12 0 23 Aug 2023
FilterFL: Knowledge Filtering-based Data-Free Backdoor Defense for Federated Learning Yanxin Yang Ming Hu Yue Cao Jun Xia Pengyu Zhang Yihao Huang Xiao He FedML 308 6 0 22 Aug 2023
Temporal-Distributed Backdoor Attack Against Video Based Action RecognitionAAAI Conference on Artificial Intelligence (AAAI), 2023 Xi Li Songhe Wang Rui Huang Mahanth K. Gowda G. Kesidis AAML 340 7 0 21 Aug 2023
Test-Time Backdoor Defense via Detecting and Repairing Jiyang Guan Jian Liang Ran He AAML 172 0 0 11 Aug 2023
Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time DetectionInternational Workshop on Machine Learning for Signal Processing (MLSP), 2023 Hang Wang Zhen Xiang David J. Miller G. Kesidis AAML 76 3 0 08 Aug 2023
Backdoor Federated Learning by Poisoning Backdoor-Critical LayersInternational Conference on Learning Representations (ICLR), 2023 Haomin Zhuang Mingxian Yu Hao Wang Yang Hua Jian Li Xu Yuan FedML 169 26 0 08 Aug 2023
TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored ModelsIEEE International Conference on Computer Vision (ICCV), 2023 Indranil Sur Karan Sikka Matthew Walmer K. Koneripalli Anirban Roy Xiaoyu Lin Ajay Divakaran Susmit Jha 143 12 0 07 Aug 2023
On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and OutlookInternational Journal of Computer Vision (IJCV), 2023 Mingyuan Fan Chengyu Wang Cen Chen Yang Liu Jun Huang HILM 243 11 0 31 Jul 2023
Beating Backdoor Attack at Its Own GameIEEE International Conference on Computer Vision (ICCV), 2023 Min Liu Alberto L. Sangiovanni-Vincentelli Xiangyu Yue AAML 468 13 0 28 Jul 2023
Backdoor Attacks for In-Context Learning with Language Models Nikhil Kandpal Matthew Jagielski Florian Tramèr Nicholas Carlini SILM AAML 298 110 0 27 Jul 2023
Backdoor Attacks against Voice Recognition Systems: A SurveyACM Computing Surveys (ACM Comput. Surv.), 2023 Baochen Yan Jiahe Lan Zheng Yan AAML 182 18 0 23 Jul 2023
Adversarial Feature Map Pruning for BackdoorInternational Conference on Learning Representations (ICLR), 2023 Dong Huang Qingwen Bu AAML 153 5 0 21 Jul 2023