Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning

Authors: Georg Pichler, Marco Romanelli, Leonardo Rey Vega, Pablo Piantanida

Source: IEEE Transactions on Dependable and Secure Computing. 21:4290-4296

Subject Terms: FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial intelligence, Computer Science - Cryptography and Security, Computer Science - Artificial Intelligence, Set (abstract data type), Evolutionary biology, 02 engineering and technology, MNIST database, Epistemology, Contrast (vision), LEARNING, Adversarial Robustness in Deep Learning Models, Machine Learning (cs.LG), Deep Learning, Inference, Artificial Intelligence, Machine learning, 0202 electrical engineering, electronic engineering, information engineering, FEDERATED, Data mining, Biology, NEURAL NET, Membership Inference Attacks, Chromatography, Sample (material), Privacy-Preserving Techniques for Data Analysis and Machine Learning, Deep learning, Computer science, FOS: Philosophy, ethics and religion, Programming language, Philosophy, Chemistry, Artificial Intelligence (cs.AI), Function (biology), Computer Science, Physical Sciences, Simple (philosophy), MEMBERSHIP INFERENCE, Cryptography and Security (cs.CR), Federated Learning, Training set

File Description: application/pdf

Access URL: http://arxiv.org/abs/2203.16463
http://hdl.handle.net/11336/255711

A lightweight multi-task learning network based on key area guidance for counterfeit detection

Authors: Sam Yang, Yu Yang, Lei Zhou, Jixin Zou

Source: Signal, Image and Video Processing. 18:4675-4685

Subject Terms: FOS: Political science, FOS: Law, Automated Currency Recognition and Authentication, 02 engineering and technology, Pattern Recognition, Adversarial Robustness in Deep Learning Models, Counterfeit, Systems engineering, Task (project management), Resampling Detection, Engineering, Artificial Intelligence, Computer security, Image Forgery Detection, 0202 electrical engineering, electronic engineering, information engineering, Counterfeit Detection, Key (lock), Embedded system, Political science, Human–computer interaction, 15. Life on land, Computer science, Tampering Localization, Computer Science, Physical Sciences, Computer Vision and Pattern Recognition, Digital Image Forgery Detection and Identification, Law

Survey on Machine Learning Biases and Mitigation Techniques

Authors: Sunzida Siddique, Mohd Ariful Haque, Roy George, Kishor Datta Gupta, Debashis Gupta, Md Jobair Hossain Faruk

Source: Digital, Vol 4, Iss 1, Pp 1-68 (2023)

Subject Terms: Artificial intelligence, bias, Explainable Artificial Intelligence, Resource (disambiguation), Variety (cybernetics), 02 engineering and technology, Adversarial Robustness in Deep Learning Models, Adversarial system, 7. Clean energy, Learning with Noisy Labels in Machine Learning, Data science, Machine Learning, Context (archaeology), Engineering, Artificial Intelligence, Meta-Learning, Machine learning, fairness constraints, 0202 electrical engineering, electronic engineering, information engineering, FOS: Mathematics, Pathology, Risk analysis (engineering), 10. No inequality, Biology, Selection bias, pre-processing, Computer network, 4. Education, Statistics, Paleontology, QA75.5-76.95, Computer science, Management science, Programming language, machine learning, Electronic computers. Computer science, Computer Science, Physical Sciences, 8. Economic growth, Data collection, mitigation techniques, Medicine, Pipeline (software), in-processing, Mathematics, Robust Learning

Access URL: https://doaj.org/article/6d141a6735f84846ad483c27550fccee

A resampling-based method to evaluate NLI models

Authors: Felipe Salvatore, Marcelo Finger, Roberto Hirata, Alexandre G. Patriota

Source: Natural Language Engineering. 30:793-820

Subject Terms: Neural Machine Translation, Artificial intelligence, Resampling, Equivalence (formal languages), Generalization, Set (abstract data type), Adversarial Robustness in Deep Learning Models, Adversarial system, 01 natural sciences, Mathematical analysis, Deep Learning, 0504 sociology, Inference, Artificial Intelligence, Machine learning, FOS: Mathematics, 0101 mathematics, Natural Language Processing, Geography, Topic Modeling, Test set, 4. Education, 05 social sciences, Statistical Machine Translation and Natural Language Processing, Discrete mathematics, Computer science, Language Modeling, Programming language, Adversarial Examples, Computer Science, Physical Sciences, Benchmark (surveying), Mathematics, Geodesy

FedSlice: Protecting Federated Learning Models from Malicious Participants with Model Slicing

Authors: Ziqi Zhang, Yuanchun Li, Bingyan Liu, Yong Cai, Li Ding, Yao Guo, Xiangqun Chen

Source: 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE). :460-472

Subject Terms: Artificial neural network, Artificial intelligence, Encryption, Adversarial Robustness in Deep Learning Models, Adversarial system, 7. Clean energy, Hacker, Inference, Artificial Intelligence, Computer security, Client-side, Differential Privacy, 10. No inequality, Secure Computation, Membership Inference Attacks, Threat model, Computer network, 4. Education, Privacy-Preserving Techniques for Data Analysis and Machine Learning, 16. Peace & justice, Computer science, World Wide Web, Operating system, Machine Learning for Internet Traffic Classification, Computer Science, Physical Sciences, Crowdsourcing, Federated Learning, Software, Server-side

R-CNN and YOLOV4 based Deep Learning Model for intelligent detection of weaponries in real time video

Authors: K. P. Vijayakumar, K. Pradeep, A. Balasundaram, A. P. Dhande

Source: Mathematical Biosciences and Engineering, Vol 20, Iss 12, Pp 21611-21625 (2023)

Subject Terms: yolov4, Artificial neural network, Artificial intelligence, Outlier Detection, Convolutional neural network, security, Adversarial Robustness in Deep Learning Models, Pattern recognition (psychology), 7. Clean energy, Real-time computing, Anomaly Detection in High-Dimensional Data, Deep Learning, Resampling Detection, Convolution (computer science), Artificial Intelligence, Computer security, QA1-939, Image Forgery Detection, cnn, Camera Model Identification, deep learning, Deep learning, 16. Peace & justice, Computer science, Computer Science, Physical Sciences, weapon detection, Computer vision, Computer Vision and Pattern Recognition, Digital Image Forgery Detection and Identification, TP248.13-248.65, Mathematics, Biotechnology

Access URL: https://pubmed.ncbi.nlm.nih.gov/38124612
https://doaj.org/article/7181d12692d64942b4a4570a2580a5f4

An Optimised Defensive Technique to Recognize Adversarial Iris Images Using Curvelet Transform

Authors: K. Meenakshi, G. Maragatham

Source: Intelligent Automation & Soft Computing. 35:627-643

Subject Terms: Artificial intelligence, Support vector machine, Convolutional neural network, 02 engineering and technology, Adversarial Robustness in Deep Learning Models, Adversarial system, Pattern recognition (psychology), 7. Clean energy, Identification (biology), Resampling Detection, Artificial Intelligence, Machine learning, Image Forgery Detection, 0202 electrical engineering, electronic engineering, information engineering, 10. No inequality, Biology, Camera Model Identification, Geography, 4. Education, Iris Recognition, Botany, Biometric Recognition and Security Systems, Deep learning, Face Spoof Detection, Computer science, 3. Good health, Biometrics, Signal Processing, Computer Science, Physical Sciences, Computer vision, Wavelet transform, Computer Vision and Pattern Recognition, Curvelet, Digital Image Forgery Detection and Identification, Benchmark (surveying), Wavelet, Geodesy

Robustness-Aware Word Embedding Improves Certified Robustness to Adversarial Word Substitutions

Authors: Yibin Wang, Yichen Yang, Di He, Kai He

Source: Findings of the Association for Computational Linguistics: ACL 2023. :673-687

Subject Terms: Artificial intelligence, Natural language processing, Robustness (evolution), Word (group theory), Word embedding, Geometry, Adversarial Robustness in Deep Learning Models, Computer science, Biochemistry, Gene, Chemistry, Artificial Intelligence, Computer Science, Physical Sciences, FOS: Mathematics, Robustness, Mathematics, Embedding

Not All Counterhate Tweets Elicit the Same Replies: A Fine-Grained Analysis

Authors: Abdullah Albanyan, Ahmed E. Hassan, Eduardo Blanco

Source: Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023). :71-88

Subject Terms: Social Sciences, Epistemology, Adversarial Robustness in Deep Learning Models, Argument (complex analysis), Social psychology, Mathematical analysis, Biochemistry, Artificial Intelligence, Automated Detection of Hate Speech and Offensive Language, Hate Speech, FOS: Mathematics, Psychology, The Impact of Digital Media on Public Discourse, 10. No inequality, Communication, 4. Education, Linguistics, Limit (mathematics), 16. Peace & justice, Computer science, FOS: Philosophy, ethics and religion, Aggression, FOS: Psychology, Philosophy, Chemistry, Computer Science, Physical Sciences, FOS: Languages and literature, Mathematics

Alpha Fusion Adversarial Attack Analysis Using Deep Learning

Authors: Mohibullah Khan, Ata Ullah, Isra Naz, Sajjad Haider, Nz Jhanji, Mohammad Shorfuzzaman, Mehedi Masud

Source: Computer Systems Science and Engineering. 46:461-473

Subject Terms: Artificial neural network, Radiology, Nuclear Medicine and Imaging, Artificial intelligence, Psychometrics, Convolutional neural network, 02 engineering and technology, Adversarial Robustness in Deep Learning Models, Pattern recognition (psychology), Adversarial system, Alpha (finance), Anomaly Detection in High-Dimensional Data, Identification (biology), Deep Learning, Segmentation, Artificial Intelligence, Health Sciences, Machine learning, FOS: Mathematics, 0202 electrical engineering, electronic engineering, information engineering, Biology, Construct validity, 4. Education, Statistics, Botany, Deep learning, Transfer Learning, Applications of Deep Learning in Medical Imaging, Computer science, 3. Good health, Adversarial Examples, Computer Science, Physical Sciences, Medicine, Feature extraction, Mathematics

Defending Adversarial Examples by a Clipped Residual U-Net Model

Authors: Kazim Ali, Adnan N. Qureshi, Muhammad Shahid Bhatti, Abid Sohail, Mohammad Hijji

Source: Intelligent Automation & Soft Computing. 35:2237-2256

Subject Terms: Artificial neural network, Artificial intelligence, Computer Vision, Geometry, Convolutional neural network, MNIST database, 02 engineering and technology, Adversarial Robustness in Deep Learning Models, Adversarial system, Pattern recognition (psychology), 7. Clean energy, Anomaly Detection in High-Dimensional Data, Net (polyhedron), Deep Learning, Artificial Intelligence, Machine learning, FOS: Mathematics, 0202 electrical engineering, electronic engineering, information engineering, Neural Network Architectures, Deep learning, Computer science, 3. Good health, Algorithm, Adversarial Examples, Residual, Computer Science, Physical Sciences, Deep Learning in Computer Vision and Image Recognition, Computer Vision and Pattern Recognition, Defenses, Mathematics

Associative Discussion Among Generating Adversarial Samples Using Evolutionary Algorithm and Samples Generated Using GAN

Authors: Aruna Pavate, Rajesh Bansode, Parvathaneni Naga Srinivasu, Jana Shafi, Jaeyoung Choi, Muhammad Fazal Ijaz

Source: IEEE Access, Vol 11, Pp 143757-143770 (2023)

Subject Terms: Artificial neural network, Artificial intelligence, Adversarial Robustness in Deep Learning Models, Adversarial system, Pattern recognition (psychology), Anomaly Detection in High-Dimensional Data, attacks, Engineering, Deep Learning, Artificial Intelligence, Deep neural networks, Machine learning, FOS: Electrical engineering, electronic engineering, information engineering, Electrostatic Discharge Protection in Integrated Circuits, differential evolutionary algorithm, Electrical and Electronic Engineering, Chromatography, Sample (material), Deep learning, Computer science, TK1-9971, Algorithm, Chemistry, deep neural networks, Adversarial Examples, generative adversary networks, Adversarial examples, Computer Science, Physical Sciences, optimization methods, Electrical engineering. Electronics. Nuclear engineering, Generative adversarial network

Access URL: https://doaj.org/article/1b78d58d9269482f90ece26fbeac1123

MIL-Decoding: Detoxifying Language Models at Token-Level via Multiple Instance Learning

Authors: Xu Zhang, Xiaojun Wan

Source: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). :190-202

Subject Terms: Artificial neural network, Artificial intelligence, Recurrent neural network, Speech recognition, Adversarial Robustness in Deep Learning Models, Deep Learning, Context (archaeology), Artificial Intelligence, Computer security, Machine learning, Psychology, Biology, Natural language processing, Paleontology, Computer science, Language model, Mathematics education, 6. Clean water, 3. Good health, Algorithm, FOS: Psychology, Security token, Computer Science, Physical Sciences, Fluency, Decoding methods

Attacking neural machine translations via hybrid attention learning

Authors: Mingze Ni, Ce Wang, Tianqing Zhu, Shui Yu, Wei Liu

Source: Machine Learning. 111:3977-4002

Subject Terms: Artificial neural network, Neural Machine Translation, Artificial intelligence, Robustness (evolution), 02 engineering and technology, Adversarial Robustness in Deep Learning Models, Adversarial system, Biochemistry, Gene, Machine Translation, Artificial Intelligence, Deep neural networks, Machine learning, 0202 electrical engineering, electronic engineering, information engineering, Machine translation, Multilingual Neural Machine Translation, Natural Language Processing, Natural language processing, Deep learning, Statistical Machine Translation and Natural Language Processing, Computer science, Language Modeling, Chemistry, Adversarial Examples, Computer Science, Physical Sciences

Multiple Adversarial Domains Adaptation Approach for Mitigating Adversarial Attacks Effects

Authors: Bader Rasheed, Adil Khan, Muhammad Ahmad, Manuel Mazzara, S. M. Ahsan Kazmi

Source: International Transactions on Electrical Energy Systems, Vol 2022 (2022)

Subject Terms: Artificial neural network, Artificial intelligence, Materials Science, Robustness (evolution), Overfitting, MNIST database, 02 engineering and technology, Adversarial Robustness in Deep Learning Models, Adversarial system, Biochemistry, Gene, Artificial Intelligence, Machine learning, Deep neural networks, Materials Chemistry, 0202 electrical engineering, electronic engineering, information engineering, Nuclear Fuel Development, Domain adaptation, Adaptation (eye), Physics, Optics, Computer science, TK1-9971, Chemistry, Adversarial Examples, Computer Science, Physical Sciences, Electrical engineering. Electronics. Nuclear engineering, Defenses, Classifier (UML)

File Description: text/xhtml

Access URL: https://doaj.org/article/6b53e280f12743058d37e3a2db5d1937

Toward Improved Reliability of Deep Learning Based Systems Through Online Relabeling of Potential Adversarial Attacks

Authors: Shawqi Al-Maliki, Faissal El Bouanani, Kashif Ahmad, Mohamed Abdallah, Dinh Thai Hoang, Dusit Niyato, Ala Al-Fuqaha

Source: IEEE Transactions on Reliability. 72:1367-1382

Subject Terms: Artificial intelligence, Outlier Detection, Robustness (evolution), Adversarial Robustness in Deep Learning Models, Adversarial system, Biochemistry, Quantum mechanics, Gene, Anomaly Detection in High-Dimensional Data, Deep Learning, Artificial Intelligence, Deep neural networks, Machine learning, Robustness, Data mining, Geography, Physics, Deep learning, Upload, Power (physics), Computer science, World Wide Web, Operating system, Chemistry, Reliability (semiconductor), Adversarial Examples, Computer Science, Physical Sciences, Crowdsourcing, Defenses, Benchmark (surveying), Geodesy

Access URL: https://www.techrxiv.org/articles/preprint/Opportunistic_Use_of_Crowdsourced_Workers_for_Online_Relabeling_of_Potential_Adversarial_Examples/17088941/files/31600043.pdf

Continuous Engineering for Trustworthy Learning-Enabled Autonomous Systems

Authors: Saddek Bensalem, Panagiotis Katsaros, Dejan Ničković, Brian Liao, Ricardo Ruiz Nolasco, Mohamed M. Ahmed, Tewodros A. Beyene, Filip Cano, Antoine Delacourt, Hasan Esen, Alexandru Forrai, Weicheng He, Xiaowei Huang, Nikolaos Kekatos, Bettina Könighofer, Michael Paulitsch, Doron Peled, Matthieu Ponchant, Lev Sorokin, S. Y. Tong, Changshun Wu

Source: Lecture Notes in Computer Science ISBN: 9783031460012

Subject Terms: Software engineering, Automated Software Testing Techniques, 9. Industry and infrastructure, 4. Education, Reliability Evaluation, Adversarial Robustness in Deep Learning Models, Computer science, 7. Clean energy, Systems engineering, Fault Tolerance in Electronic Systems, Engineering, Aerospace engineering, Artificial Intelligence, Computer security, Computer Science, Physical Sciences, 11. Sustainability, FOS: Electrical engineering, electronic engineering, information engineering, Telecommunications, Software deployment, Electrical and Electronic Engineering, Software, Trustworthiness, Frame (networking), Automotive industry

A Deep Learning Powered System to Lie Detection While Online Study

Authors: Lê Quang Thảo, Duong Duc Cuong, Nguyen Nhan Nhi, Nguyen Duc Tam

Source: Traitement du Signal. 39:893-898

Subject Terms: Artificial intelligence, Usability, Handling Imbalanced Data in Classification Problems, Infectious disease (medical specialty), Adversarial Robustness in Deep Learning Models, Social psychology, 7. Clean energy, 12. Responsible consumption, Anomaly Detection in High-Dimensional Data, Deep Learning, Artificial Intelligence, Cheating, Machine learning, FOS: Mathematics, Pathology, Psychology, Disease, 0501 psychology and cognitive sciences, 10. No inequality, Cost-Sensitive Learning, Human–computer interaction, 4. Education, Statistics, 05 social sciences, Deep learning, Predictability, Computer science, 3. Good health, Coronavirus disease 2019 (COVID-19), FOS: Psychology, Multimedia, Online learning, Computer Science, Physical Sciences, Medicine, Lying, Radiology, Mathematics

A federated learning framework for cyberattack detection in vehicular sensor networks

Authors: Maha Driss, Iman Almomani, Zil e Huma, Jawad Ahmad

Source: Complex & Intelligent Systems. 8:4221-4235

Subject Terms: Artificial intelligence, Internet of Things, Vehicular Ad Hoc Networks, 02 engineering and technology, Adversarial Robustness in Deep Learning Models, Mathematical analysis, Intelligent Transportation Systems, Internet of Vehicles, Engineering, Artificial Intelligence, Computer security, FOS: Electrical engineering, electronic engineering, information engineering, FOS: Mathematics, 0202 electrical engineering, electronic engineering, information engineering, Electrical and Electronic Engineering, Secure Computation, Scheme (mathematics), Computer network, Privacy-Preserving Techniques for Data Analysis and Machine Learning, Deep learning, Computer science, Cybersecurity, Internet of things, Intrusion detection, Vehicular sensor networks, Computer Science, Physical Sciences, Vehicular Ad Hoc Networks and Communications, Federated Learning, Mathematics

File Description: PDF

Improving diversity and quality of adversarial examples in adversarial transformation network

Authors: Duc-Anh Nguyen, Kha Do Minh, Khoi Le, Le-Minh Nguyen, Phạm Ngọc Hưng

Source: Soft Computing. 27:3689-3706

Subject Terms: Artificial intelligence, Outlier Detection, Feature (linguistics), FOS: Political science, Norm (philosophy), Convolutional neural network, FOS: Law, Epistemology, MNIST database, 02 engineering and technology, Adversarial Robustness in Deep Learning Models, Adversarial system, Pattern recognition (psychology), Anomaly Detection in High-Dimensional Data, Machine Learning, 03 medical and health sciences, Engineering, Resampling Detection, 0302 clinical medicine, Artificial Intelligence, Machine learning, FOS: Electrical engineering, electronic engineering, information engineering, FOS: Mathematics, 0202 electrical engineering, electronic engineering, information engineering, Heuristics, Electrostatic Discharge Protection in Integrated Circuits, Electrical and Electronic Engineering, Political science, Mathematical optimization, Linguistics, Deep learning, Autoencoder, Computer science, FOS: Philosophy, ethics and religion, Algorithm, Philosophy, Operating system, Adversarial Examples, Computer Science, Physical Sciences, Quality (philosophy), FOS: Languages and literature, Computer Vision and Pattern Recognition, Pixel, Digital Image Forgery Detection and Identification, Sensor Pattern Noise, Law, Mathematics