000 06141nam a22006375i 4500
001 978-981-99-9785-5
003 DE-He213
005 20240423130322.0
007 cr nn 008mamaa
008 240203s2024 si | s |||| 0|eng d
020 _a9789819997855
_9978-981-99-9785-5
024 7 _a10.1007/978-981-99-9785-5
_2doi
050 4 _aQ334-342
050 4 _aTA347.A78
072 7 _aUYQ
_2bicssc
072 7 _aCOM004000
_2bisacsh
072 7 _aUYQ
_2thema
082 0 4 _a006.3
_223
245 1 0 _aArtificial Intelligence Security and Privacy
_h[electronic resource] :
_bFirst International Conference on Artificial Intelligence Security and Privacy, AIS&P 2023, Guangzhou, China, December 3–5, 2023, Proceedings, Part I /
_cedited by Jaideep Vaidya, Moncef Gabbouj, Jin Li.
250 _a1st ed. 2024.
264 1 _aSingapore :
_bSpringer Nature Singapore :
_bImprint: Springer,
_c2024.
300 _aXV, 595 p. 167 illus., 147 illus. in color.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aLecture Notes in Computer Science,
_x1611-3349 ;
_v14509
505 0 _aFine-grained Searchable Encryption Scheme -- Fine-grained Authorized Secure Deduplication with Dynamic Policy -- Deep Multi-Image Hiding with Random Key -- Member Inference Attacks in Federated Contrastive Learning -- A network traffic anomaly detection method based on shapelet and KNN -- DFaP: Data Filtering and Purification Against Backdoor Attacks -- A Survey of Privacy Preserving Subgraph Matching Method -- The Analysis of Schnorr Multi-Signatures and the Application to AI -- Active Defense against Image Steganography -- Strict Differentially Private Support Vector Machines with Dimensionality Reduction -- Converging Blockchain and Deep Learning in UAV Network Defense Strategy: Ensuring Data Security During Flight -- Towards Heterogeneous Federated Learning: Analysis, Solutions, and Future Directions -- From Passive Defense to Proactive Defence: Strategies and Technologies -- Research on Surface Defect Detection System of Chip Inductors Based on Machine Vision -- Multimodal fatigue detectionin drivers via physiological and visual signals -- Protecting Bilateral Privacy in Machine Learning-as-a-Service: A Differential Privacy Based Defense -- FedCMK: An Efficient Privacy-Preserving Federated Learning Framework -- An embedded cost learning framework based on cumulative gradient -- An Assurance Case Practice of AI-enabled Systems on Maritime Inspection -- Research and Implementation of EXFAT File System Reconstruction Algorithm Based on Cluster Size Assumption and Computational Verification -- A Verifiable Dynamic Multi-Secret Sharing Obfuscation Scheme Applied to Data LakeHouse -- DZIP: A Data Deduplication-Compatible Enhanced Version of Gzip -- Efficient Wildcard Searchable Symmetric Encryption with Forward and Backward Security -- Adversarial Attacks against Object Detection in Remote Sensing Images -- Hardware Implementation and Optimization of Critical Modules of SM9 Digital Signature Algorithm -- Post-quantum Dropout-resilient Aggregation for Federated Learning via Lattice-basedPRF -- Practical and Privacy-Preserving Decision Tree Evaluation with One Round Communication -- IoT-Inspired Education 4.0 Framework for Higher Education and Industry Needs -- Multi-agent Reinforcement Learning Based User-Centric Demand Response with Non-Intrusive Load Monitoring -- Decision Poisson: From universal gravitation to offline reinforcement learning -- SSL-ABD:An Adversarial Defense MethodAgainst Backdoor Attacks in Self-supervised Learning -- Personalized Differential Privacy in the Shuffle Model -- MKD: Mutual Knowledge Distillation for Membership Privacy Protection -- Fuzzing Drone Control System Configurations Based on Quality-Diversity Enhanced Genetic Algorithm -- KEP: Keystroke Evoked Potential for EEG-based User Authentication -- Verifiable Secure Aggregation Protocol under Federated Learning -- Electronic voting privacy protection scheme based on double signature in Consortium Blockchain -- Securing 5G Positioning via Zero Trust Architecture -- Email Reading Behavior-informed Machine Learning Model to Predict Phishing Susceptibility. .
520 _aThis two-volume set LNCS 14509-14510, constitutes the refereed proceedings of the First International Conference on Artificial Intelligence Security and Privacy, AIS&P 2023, held in Guangzhou, China, during December 3–5, 2023. The 40 regular papers and 23 workshop papers presented in this two-volume set were carefully reviewed and selected from 115 submissions. Topics of interest include, e.g., attacks and defence on AI systems; adversarial learning; privacy-preserving data mining; differential privacy; trustworthy AI; AI fairness; AI interpretability; cryptography for AI; security applications. .
650 0 _aArtificial intelligence.
650 0 _aSecurity systems.
650 0 _aData protection
_xLaw and legislation.
650 0 _aCryptography.
650 0 _aData encryption (Computer science).
650 0 _aData protection.
650 1 4 _aArtificial Intelligence.
650 2 4 _aSecurity Science and Technology.
650 2 4 _aPrivacy.
650 2 4 _aCryptology.
650 2 4 _aSecurity Services.
700 1 _aVaidya, Jaideep.
_eeditor.
_4edt
_4http://id.loc.gov/vocabulary/relators/edt
700 1 _aGabbouj, Moncef.
_eeditor.
_4edt
_4http://id.loc.gov/vocabulary/relators/edt
700 1 _aLi, Jin.
_eeditor.
_4edt
_4http://id.loc.gov/vocabulary/relators/edt
710 2 _aSpringerLink (Online service)
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9789819997848
776 0 8 _iPrinted edition:
_z9789819997862
830 0 _aLecture Notes in Computer Science,
_x1611-3349 ;
_v14509
856 4 0 _uhttps://doi.org/10.1007/978-981-99-9785-5
912 _aZDB-2-SCS
912 _aZDB-2-SXCS
912 _aZDB-2-LNC
942 _cSPRINGER
999 _c187321
_d187321