{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:11:09Z","timestamp":1784131869072,"version":"3.55.0"},"reference-count":78,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Information Security and Applications"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.jisa.2026.104517","type":"journal-article","created":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T01:25:40Z","timestamp":1780104340000},"page":"104517","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Model X-Ray: Detection of hidden malware in AI model weights using few shot learning"],"prefix":"10.1016","volume":"101","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9274-802X","authenticated-orcid":false,"given":"Daniel","family":"Gilkarov","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2055-2211","authenticated-orcid":false,"given":"Ran","family":"Dubin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.jisa.2026.104517_bib0001","doi-asserted-by":"crossref","first-page":"1320","DOI":"10.1109\/TPAMI.2016.2587642","article-title":"DeepID-net: object detection with deformable part based convolutional neural networks","volume":"39","author":"Ouyang","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.jisa.2026.104517_bib0002","doi-asserted-by":"crossref","unstructured":"Noh H., Hong S., Han B.. Learning deconvolution network for semantic segmentation. In: 2015\u202fIEEE International conference on computer vision (ICCV). Los Alamitos, CA, USA: IEEE Computer Society; 2015, p\u2018p. 1520\u20131528. 10.1109\/ICCV.2015.178.","DOI":"10.1109\/ICCV.2015.178"},{"key":"10.1016\/j.jisa.2026.104517_bib0003","unstructured":"Devlin J., Chang M.-W., Lee K., Toutanova K.. BERT: pre-training of deep bidirectional transformers for language understanding. 2019. arXiv: 1810.04805."},{"key":"10.1016\/j.jisa.2026.104517_bib0004","series-title":"2015\u202fIEEE International conference on robotics and automation (ICRA)","first-page":"3223","article-title":"Deep learning helicopter dynamics models","author":"Punjani","year":"2015"},{"key":"10.1016\/j.jisa.2026.104517_bib0005","series-title":"Proceedings of the twenty-ninth AAAI conference on artificial intelligence (AAAI\u201915)","first-page":"3686","article-title":"Robot learning manipulation action plans by \u201cwatching\u201d unconstrained videos from the world wide web","author":"Yang","year":"2015"},{"key":"10.1016\/j.jisa.2026.104517_bib0006","unstructured":"OpenAI. ChatGPT: a large-scale generative model for conversation, 2022. https:\/\/openai.com\/research\/chatgpt."},{"key":"10.1016\/j.jisa.2026.104517_bib0007","unstructured":"HuggingFace. Fickling pickle scanning. 2022. Accessed: 2022-12-19, https:\/\/huggingface.co\/."},{"key":"10.1016\/j.jisa.2026.104517_bib0008","unstructured":"TensorFlow. TensorFlow hub. 2022. Accessed: 2022-12-19, https:\/\/www.tensorflow.org\/hub."},{"key":"10.1016\/j.jisa.2026.104517_bib0009","unstructured":"Jeddi A., Shafiee M.J., Wong A.. A simple fine-tuning is all you need: towards robust deep learning via adversarial fine-tuning. 2020. arXiv: 2012.13628."},{"key":"10.1016\/j.jisa.2026.104517_bib0010","series-title":"2021\u202fIEEE Symposium on computers and communications (ISCC)","first-page":"1","article-title":"EvilModel: hiding malware inside of neural network models","author":"Wang","year":"2021"},{"key":"10.1016\/j.jisa.2026.104517_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.cose.2022.102807","article-title":"EvilModel 2.0: bringing neural network models into malware attacks","volume":"120","author":"Wang","year":"2022","journal-title":"Comput Secur"},{"key":"10.1016\/j.jisa.2026.104517_bib0012","series-title":"Annual computer security applications conference","first-page":"928","article-title":"StegoNet: turn deep neural network into a stegomalware","author":"Liu","year":"2020"},{"key":"10.1016\/j.jisa.2026.104517_bib0013","series-title":"Insecure deserialization detection in python","author":"Verma","year":"2023"},{"key":"10.1016\/j.jisa.2026.104517_bib0014","doi-asserted-by":"crossref","unstructured":"Hitaj D., Pagnotta G., Hitaj B., Mancini L.V., Perez-Cruz F.. MaleficNet: hiding malware into deep neural networks using spread-spectrum channel coding. In: Computer security \u2013 ESORICS 2022: 27th European symposium on research in computer security, Copenhagen, Denmark, September 26\u201330, 2022, Proceedings, Part III. Berlin, Heidelberg: Springer-Verlag. 2022, pp. 425\u2013444. 10.1007\/978-3-031-17143-7_21.","DOI":"10.1007\/978-3-031-17143-7_21"},{"key":"10.1016\/j.jisa.2026.104517_bib0015","unstructured":"CyberTalk. Hackers hide malware in windows logo, 2022. https:\/\/www.cybertalk.org\/2022\/09\/30\/hackers-hide-malware-in-windows-logo\/."},{"key":"10.1016\/j.jisa.2026.104517_bib0016","unstructured":"Cimpanu C.. WAV audio files are now being used to hide malicious code. https:\/\/www.zdnet.com\/article\/wav-audio-files-are-now-being-used-to-hide-malicious-code\/; 2019."},{"key":"10.1016\/j.jisa.2026.104517_bib0017","unstructured":"Wang Z., Byrnes O., Wang H., Sun R., Ma C., Chen H., et al. Data hiding with deep learning: a survey unifying digital watermarking and steganography. arXiv: 2107.092872021."},{"key":"10.1016\/j.jisa.2026.104517_bib0018","doi-asserted-by":"crossref","first-page":"23409","DOI":"10.1109\/ACCESS.2021.3053998","article-title":"Image steganography: a review of the recent advances","volume":"9","author":"Subramanian","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.jisa.2026.104517_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.cosrev.2020.100316","article-title":"Digital audio steganography: systematic review, classification, and analysis of the current state of the art","volume":"38","author":"AlSabhany","year":"2020","journal-title":"Comput Sci Rev"},{"key":"10.1016\/j.jisa.2026.104517_bib0020","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/j.neucom.2018.09.091","article-title":"Video steganography: a review","volume":"335","author":"Liu","year":"2019","journal-title":"Neurocomputing"},{"issue":"21","key":"10.1016\/j.jisa.2026.104517_bib0021","doi-asserted-by":"crossref","first-page":"2829","DOI":"10.3390\/math9212829","article-title":"A review on text steganography techniques","volume":"9","author":"Majeed","year":"2021","journal-title":"Mathematics"},{"key":"10.1016\/j.jisa.2026.104517_bib0022","series-title":"2020 4th international conference on trends in electronics and informatics (ICOEI)(48184)","first-page":"64","article-title":"A survey on steganography using least significant bit (LSB) embedding approach","author":"Bansal","year":"2020"},{"key":"10.1016\/j.jisa.2026.104517_bib0023","doi-asserted-by":"crossref","first-page":"4767","DOI":"10.1109\/TIFS.2024.3383770","article-title":"Steganalysis of AI models LSB attacks","volume":"19","author":"Gilkarov","year":"2024","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"10.1016\/j.jisa.2026.104517_bib0024","doi-asserted-by":"crossref","first-page":"124295","DOI":"10.1109\/ACCESS.2023.3330141","article-title":"Disarming attacks inside neural network models","volume":"11","author":"Dubin","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.jisa.2026.104517_bib0025","doi-asserted-by":"crossref","unstructured":"Amit G., Levy M., Mirsky Y.. Transpose attack: stealing datasets with bidirectional training. 2023. arXiv: 2311.07389.","DOI":"10.14722\/ndss.2024.23325"},{"key":"10.1016\/j.jisa.2026.104517_bib0026","unstructured":"Neyshabur B., Bhojanapalli S., McAllester D., Srebro N.. Exploring generalization in deep learning. 2017. arXiv: 1706.08947."},{"key":"10.1016\/j.jisa.2026.104517_bib0027","unstructured":"Gilkarov D., Dubin R.. AI model steganalysis. https:\/\/github.com\/ArielCyber\/AI_Model_Steganalysis; 2023."},{"issue":"4","key":"10.1016\/j.jisa.2026.104517_bib0028","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1109\/TPAMI.2006.79","article-title":"One-shot learning of object categories","volume":"28","author":"Fei-Fei","year":"2006","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.jisa.2026.104517_bib0029","doi-asserted-by":"crossref","unstructured":"Shaban A., Bansal S., Liu Z., Essa I., Boots B.. One-shot learning for semantic segmentation. 2017. arXiv: 1709.03410.","DOI":"10.5244\/C.31.167"},{"key":"10.1016\/j.jisa.2026.104517_bib0030","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","article-title":"Impiroved few-shot visual classificaton","author":"Bateni","year":"2020"},{"key":"10.1016\/j.jisa.2026.104517_bib0031","unstructured":"Zhou J., Zheng Y., Tang J., Li J., Yang Z.. FlipDA: effective and robust data augmentation for few-shot learning. 2022. arXiv: 2108.06332."},{"key":"10.1016\/j.jisa.2026.104517_bib0032","unstructured":"Nakamura A., Harada T.. Revisiting fine-tuning for few-shot learning. 2019. arXiv: 1910.00216."},{"issue":"10","key":"10.1016\/j.jisa.2026.104517_bib0033","first-page":"8635","article-title":"Learning a few-shot embedding model with contrastive learning","volume":"35","author":"Liu","year":"2021","journal-title":"Proc AAAI Conf Artif Intell"},{"issue":"9","key":"10.1016\/j.jisa.2026.104517_bib0034","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.3390\/sym11091066","article-title":"Deep metric learning: a survey","volume":"11","author":"Kaya","year":"2019","journal-title":"Symmetry"},{"key":"10.1016\/j.jisa.2026.104517_bib0035","series-title":"ICML deep learning workshop","article-title":"Siamese neural networks for one-shot image recognition","author":"Koch","year":"2015"},{"key":"10.1016\/j.jisa.2026.104517_bib0036","doi-asserted-by":"crossref","first-page":"1863","DOI":"10.1016\/j.procs.2019.09.358","article-title":"Malware image classification using one-shot learning with siamese networks","volume":"159","author":"Hsiao","year":"2019","journal-title":"Procedia Comput Sci"},{"issue":"5","key":"10.1016\/j.jisa.2026.104517_bib0037","doi-asserted-by":"crossref","first-page":"1181","DOI":"10.1109\/TIFS.2018.2871749","article-title":"Deep residual network for steganalysis of digital images","volume":"14","author":"Boroumand","year":"2019","journal-title":"IEEE Trans Inf Forensics Secur"},{"issue":"1","key":"10.1016\/j.jisa.2026.104517_bib0038","doi-asserted-by":"crossref","first-page":"1","DOI":"10.52396\/JUSTC-2021-0197","article-title":"Steganalysis of neural networks based on parameter statistical bias","volume":"52","author":"Yin","year":"2022","journal-title":"JUSTC"},{"key":"10.1016\/j.jisa.2026.104517_bib0039","series-title":"The workshops of the thirty-second AAAI conference on artificial intelligence","first-page":"268","article-title":"Malware detection by eating a whole EXE","author":"Raff","year":"2018"},{"key":"10.1016\/j.jisa.2026.104517_bib0040","unstructured":"Gilkarov D., Dubin R.. Model X-ray code repository. https:\/\/github.com\/danigil\/ModelXRay; 2026. Accessed: 2026-04-28."},{"issue":"2","key":"10.1016\/j.jisa.2026.104517_bib0041","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MC.1998.4655281","article-title":"Exploring steganography: seeing the unseen","volume":"31","author":"Johnson","year":"1998","journal-title":"Computer"},{"key":"10.1016\/j.jisa.2026.104517_bib0042","first-page":"23","article-title":"Hiding data in audio signal","author":"Bhattacharyya","year":"2010"},{"key":"10.1016\/j.jisa.2026.104517_bib0043","unstructured":"Wikipedia contributors. Single-precision floating-point format \u2014 wikipedia, the free encyclopedia. https:\/\/en.wikipedia.org\/w\/index.php?title=Single-precision_floating-point_formatoldid=1220802754; 2024. [Online; accessed 20-May-2024]."},{"key":"10.1016\/j.jisa.2026.104517_bib0044","unstructured":"MalwareBazaar. Malware sharing platform. 2024. Accessed: 2024-05-14; https:\/\/bazaar.abuse.ch\/."},{"key":"10.1016\/j.jisa.2026.104517_bib0045","series-title":"2016\u202fIEEE International conference on recent trends in electronics, information & communication technology (RTEICT)","first-page":"1778","article-title":"Preprocessing for image classification by convolutional neural networks","author":"Pal","year":"2016"},{"key":"10.1016\/j.jisa.2026.104517_bib0046","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"815","article-title":"FaceNet: a unified embedding for face recognition and clustering","author":"Schroff","year":"2015"},{"key":"10.1016\/j.jisa.2026.104517_bib0047","unstructured":"Kingma D.P., Ba J.. Adam: a method for stochastic optimization. 2017. arXiv: 1412.6980."},{"key":"10.1016\/j.jisa.2026.104517_bib0048","unstructured":"Wang Y., Chao W.-L., Weinberger K.Q., van der Maaten L.. SimpleShot: revisiting nearest-neighbor classification for few-shot learning. 2019. arXiv: 1911.04623."},{"key":"10.1016\/j.jisa.2026.104517_bib0049","series-title":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (KDD)","first-page":"785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen","year":"2016"},{"key":"10.1016\/j.jisa.2026.104517_bib0050","series-title":"NIST Special Publication","article-title":"A statistical test suite for random and pseudorandom number generators for cryptographic applications","author":"Rukhin","year":"2010"},{"key":"10.1016\/j.jisa.2026.104517_bib0051","series-title":"The art of computer programming, volume 2: seminumerical algorithms","author":"Knuth","year":"1997"},{"issue":"2","key":"10.1016\/j.jisa.2026.104517_bib0052","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1109\/MSP.2007.48","article-title":"Using entropy analysis to find encrypted and packed malware","volume":"5","author":"Lyda","year":"2007","journal-title":"IEEE Secur Priv"},{"issue":"1","key":"10.1016\/j.jisa.2026.104517_bib0053","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.ic.2004.02.003","article-title":"An information-theoretic model for steganography","volume":"192","author":"Cachin","year":"2004","journal-title":"Inf Comput"},{"key":"10.1016\/j.jisa.2026.104517_bib0054","series-title":"Proceedings of the international conference on image processing (ICIP)","first-page":"905","article-title":"Detecting hidden messages using higher-order statistical models","volume":"vol. 2","author":"Farid","year":"2002"},{"key":"10.1016\/j.jisa.2026.104517_bib0055","series-title":"Information hiding: 6th international workshop (IH 2004)","first-page":"67","article-title":"Feature-based steganalysis for JPEG images and its implications for future design of steganographic schemes","volume":"vol. 3200","author":"Fridrich","year":"2004"},{"key":"10.1016\/j.jisa.2026.104517_bib0056","doi-asserted-by":"crossref","unstructured":"Sch\u00fcrholt K., Taskiran D., Knyazev B., Gir\u00f3-i Nieto X., Borth D.. Model zoos: a dataset of diverse populations of neural network models. 2022. arXiv: 2209.14764.","DOI":"10.52202\/068431-2763"},{"key":"10.1016\/j.jisa.2026.104517_bib0057","unstructured":"Keras. Keras applications. 2024. Accessed: 2024-04-13; https:\/\/keras.io\/api\/applications\/."},{"key":"10.1016\/j.jisa.2026.104517_bib0058","unstructured":"Huang G., Liu Z., van der Maaten L., Weinberger K.Q.. Densely connected convolutional networks. 2018. arXiv: 1608.06993."},{"key":"10.1016\/j.jisa.2026.104517_bib0059","unstructured":"Tan M., Le Q.V.. EfficientNetv2: smaller models and faster training. 2021. arXiv: 2104.00298."},{"key":"10.1016\/j.jisa.2026.104517_bib0060","unstructured":"Howard A.G., Zhu M., Chen B., Kalenichenko D., Wang W., Weyand T., et al. MobileNets: efficient convolutional neural networks for mobile vision applications. 2017. arXiv: 1704.04861."},{"key":"10.1016\/j.jisa.2026.104517_bib0061","doi-asserted-by":"crossref","unstructured":"Sandler M., Howard A., Zhu M., Zhmoginov A., Chen L.-C.. MobileNetv2: inverted residuals and linear bottlenecks. 2019. arXiv: 1801.04381.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"10.1016\/j.jisa.2026.104517_bib0062","doi-asserted-by":"crossref","unstructured":"Howard A., Sandler M., Chu G., Chen L.-C., Chen B., Tan M., et al. Searching for MobileNetv3. 2019. arXiv: 1905.02244.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"10.1016\/j.jisa.2026.104517_bib0063","doi-asserted-by":"crossref","unstructured":"Zoph B., Vasudevan V., Shlens J., Le Q.V.. Learning transferable architectures for scalable image recognition. 2018. arXiv: 1707.07012.","DOI":"10.1109\/CVPR.2018.00907"},{"key":"10.1016\/j.jisa.2026.104517_bib0064","doi-asserted-by":"crossref","unstructured":"Szegedy C., Vanhoucke V., Ioffe S., Shlens J., Wojna Z.. Rethinking the inception architecture for computer vision. 2015. arXiv: 1512.00567.","DOI":"10.1109\/CVPR.2016.308"},{"key":"10.1016\/j.jisa.2026.104517_bib0065","doi-asserted-by":"crossref","unstructured":"Szegedy C., Ioffe S., Vanhoucke V., Alemi A.. Inception-v4, inception-resnet and the impact of residual connections on learning. 2016. arXiv: 1602.07261.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"10.1016\/j.jisa.2026.104517_bib0066","unstructured":"He K., Zhang X., Ren S., Sun J.. Deep residual learning for image recognition. 2015. arXiv: 1512.03385."},{"key":"10.1016\/j.jisa.2026.104517_bib0067","doi-asserted-by":"crossref","unstructured":"He K., Zhang X., Ren S., Sun J.. Identity mappings in deep residual networks. 2016. arXiv: 1603.05027.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"10.1016\/j.jisa.2026.104517_bib0068","doi-asserted-by":"crossref","unstructured":"Chollet F.. Xception: deep learning with depthwise separable convolutions. 2017. arXiv: 1610.02357.","DOI":"10.1109\/CVPR.2017.195"},{"issue":"60","key":"10.1016\/j.jisa.2026.104517_bib0069","doi-asserted-by":"crossref","first-page":"3021","DOI":"10.21105\/joss.03021","article-title":"Seaborn: statistical data visualization","volume":"6","author":"Waskom","year":"2021","journal-title":"J Open Source Softw"},{"key":"10.1016\/j.jisa.2026.104517_bib0070","unstructured":"Nataraj L., Karthikeyan S., Jacob G., Manjunath B.S.. Malware images: visualization and automatic classification. In: Proceedings of the 8th international symposium on visualization for cyber security. VizSec \u201911; New York, NY, USA: Association for Computing Machinery. 10.1145\/2016904.2016908."},{"issue":"1","key":"10.1016\/j.jisa.2026.104517_bib0071","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/s11416-018-0323-0","article-title":"Using convolutional neural networks for classification of malware represented as images","volume":"15","author":"Gibert","year":"2019","journal-title":"J Comput Virol Hacking Tech"},{"key":"10.1016\/j.jisa.2026.104517_bib0072","series-title":"2018 9th IFIP international conference on new technologies, mobility and security (NTMS)","first-page":"1","article-title":"Malware classification with deep convolutional neural networks","author":"Kalash","year":"2018"},{"key":"10.1016\/j.jisa.2026.104517_bib0073","doi-asserted-by":"crossref","DOI":"10.1016\/j.cose.2020.101748","article-title":"Image-based malware classification using ensemble of CNN architectures (IMCEC)","volume":"92","author":"Vasan","year":"2020","journal-title":"Comput Secur"},{"issue":"1","key":"10.1016\/j.jisa.2026.104517_bib0074","article-title":"Image-based malware classification method with the alexnet convolutional neural network model","volume":"2023","author":"Zhao","year":"2023","journal-title":"Secur Commun Netw"},{"key":"10.1016\/j.jisa.2026.104517_bib0075","article-title":"Image-based malware representation approach with efficientnet convolutional neural networks for effective malware classification","volume":"69","author":"Chaganti","year":"2022","journal-title":"J Inf Secur Appl"},{"issue":"1","key":"10.1016\/j.jisa.2026.104517_bib0076","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1186\/s42400-023-00170-z","article-title":"Machine learning based fileless malware traffic classification using image visualization","volume":"6","author":"Demmese","year":"2023","journal-title":"Cybersecurity"},{"key":"10.1016\/j.jisa.2026.104517_bib0077","doi-asserted-by":"crossref","DOI":"10.1016\/j.cose.2021.102420","article-title":"Image-based malware classification using section distribution information","volume":"110","author":"Xiao","year":"2021","journal-title":"Comput Secur"},{"issue":"3","key":"10.1016\/j.jisa.2026.104517_bib0078","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int J Comput Vis"}],"container-title":["Journal of Information Security and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S221421262600147X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S221421262600147X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T15:46:44Z","timestamp":1784130404000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S221421262600147X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":78,"alternative-id":["S221421262600147X"],"URL":"https:\/\/doi.org\/10.1016\/j.jisa.2026.104517","relation":{},"ISSN":["2214-2126"],"issn-type":[{"value":"2214-2126","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Model X-Ray: Detection of hidden malware in AI model weights using few shot learning","name":"articletitle","label":"Article Title"},{"value":"Journal of Information Security and Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jisa.2026.104517","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"104517"}}