Abstract

Social media (SM) has emerged as a critical tool in disaster response, offering real-time visual insights through image sharing. This visual information aids responders in assessing the severity of situation and formulating effective strategies. However, the prevalence of forged images on SM poses a significant challenge, potentially misleading responders and hindering the humanitarian efforts. Therefore, it’s crucial to verify the credibility of information sourced from SM images before incorporating it into any crucial decision-making process. However, detecting forged disaster images uploaded to SM platforms presents additional challenges. These images undergo various post-processing operations including compression, which introduces additional noise and degrades image quality, thereby complicates forgery detection. This study is the first to focus on SM disaster image Forgery detection. A novel dataset named Forge Disaster is presented, comprising both authentic and forged SM images with copy-move and splicing forgeries. The primary objective of this dataset is to serve as a benchmark for evaluating novel techniques and methodologies in the domain. Additionally, this paper presents a unified approach for robust detection of both copy-move and spliced disaster images on SM. Leveraging image enhancement filters, local binary pattern (LBP) combined with discrete fourier transform (DFT), and support vector machine (SVM), the proposed approach achieved an impressive detection accuracy of 91%, outperforming existing forgery detection methods. These contributions address the growing concern of misinformation through forged images on SM platforms during disaster situations, enhancing the reliability of disaster-related information for effective response.

Keyword

Disaster response, Forgery detection, Social media, Machine learning.

Cite this article

Saleem S, Shah A, Mehrotra M.Credibility assessment of social media images shared during disasters. International Journal of Advanced Technology and Engineering Exploration. 2024;11(113):552-574. DOI:10.19101/IJATEE.2023.10102095

Refference

[1]United nations office for disaster risk reduction. Global assessment report on disaster risk reduction 2022: our world at risk: transforming governance for a resilient future. UN; 2022.

[2]Saleem S, Mehrotra M. Emergent use of artificial intelligence and social media for disaster management. In proceedings of international conference on data science and applications 2022 (pp. 195-210). Springer Singapore.

[3]Saleem S, Mehrotra M. Context-aware transfer learning approach to detect informative social media content for disaster management. International Journal of Advanced Computer Science and Applications. 2024; 15(1):680-9.

[4]Imran M, Ofli F, Caragea D, Torralba A. Using AI and social media multimodal content for disaster response and management: opportunities, challenges, and future directions. Information Processing & Management. 2020; 57(5):102261.

[5]Nguyen DT, Ofli F, Imran M, Mitra P. Damage assessment from social media imagery data during disasters. In proceedings of the international conference on advances in social networks analysis and mining 2017 (pp. 569-76). IEEE.

[6]Mouzannar H, Rizk Y, Awad M. Damage identification in social media posts using multimodal deep learning. In proceedings of the 15th ISCRAM conference, Rochester, NY, USA 2018 (pp. 1-15).

[7]Kalliatakis G, Ehsan S, Fasli M, DMconald-maier K. Displacenet: recognising displaced people from images by exploiting dominance level. In proceedings of the conference on computer vision and pattern recognition workshops 2019 (pp. 33-8). IEEE.

[8]Shah A, Varshney S, Mehrotra M. DeepMUI: a novel method to identify malicious users on online social network platforms. Concurrency and Computation: Practice and Experience. 2024; 36(3):e7917.

[9]Gupta A, Lamba H, Kumaraguru P, Joshi A. Faking sandy: characterizing and identifying fake images on twitter during hurricane sandy. In proceedings of the 22nd international conference on world wide web 2013 (pp. 729-36). IEEE.

[10]https://www.bbc.com/future/article/ 20121031-how-to-spot-a-fake-sandy-photo. Accessed 02 June 2023.

[11]https://japannews.yomiuri.co.jp/society/ general-news/20220929-61020/ Accessed 02 June 2023.

[12]Walia S, Kumar K. Digital image forgery detection: a systematic scrutiny. Australian Journal of Forensic Sciences. 2019; 51(5):488-526.

[13]Redi JA, Taktak W, Dugelay JL. Digital image forensics: a booklet for beginners. Multimedia Tools and Applications. 2011; 51:133-62.

[14]Alahmadi A, Hussain M, Aboalsamh H, Muhammad G, Bebis G, Mathkour H. Passive detection of image forgery using DCT and local binary pattern. Signal, Image and Video Processing. 2017; 11:81-8.

[15]Sun W, Zhou J, Lyu R, Zhu S. Processing-aware privacy-preserving photo sharing over online social networks. In proceedings of the 24th international conference on multimedia 2016 (pp. 581-85). ACM.

[16]Mitra A, Mohanty SP, Corcoran P, Kougianos E. A novel machine learning based method for deepfake video detection in social media. In international symposium on smart electronic systems 2020 (pp. 91-96). IEEE.

[17]Sun W, Zhou J, Li Y, Cheung M, She J. Robust high-capacity watermarking over online social network shared images. IEEE Transactions on Circuits and Systems for Video Technology. 2020; 31(3):1208-21.

[18]Imran M, Qazi U, Ofli F, Peterson S, Alam F. AI for disaster rapid damage assessment from microblogs. In proceedings of the AAAI conference on artificial intelligence 2022 (pp. 12517-23).

[19]Alam F, Alam T, Hasan MA, Hasnat A, Imran M, Ofli F. MEDIC: a multi-task learning dataset for disaster image classification. Neural Computing and Applications. 2023; 35(3):2609-32.

[20]Saleem S, Mehrotra M. An analytical framework for analyzing tweets for disaster management: case study of turkey earthquake. In 14th international conference on computing communication and networking technologies 2023 (pp. 1-7). IEEE.

[21]Alam F, Ofli F, Imran M. Processing social media images by combining human and machine computing during crises. International Journal of Human–Computer Interaction. 2018; 34(4):311-27.

[22]Alam F, Ofli F, Imran M. Crisismmd: multimodal twitter datasets from natural disasters. In proceedings of the international AAAI conference on web and social media 2018 (pp.465-73).

[23]Li X, Caragea D, Caragea C, Imran M, Ofli F. Identifying disaster damage images using a domain adaptation approach. In proceedings of the 16th international conference on information systems for crisis response and management 2019 (pp. 633-45).

[24]Ning H, Li Z, Hodgson ME, Wang C. Prototyping a social media flooding photo screening system based on deep learning. ISPRS International Journal of Geo-Information. 2020; 9(2):104.

[25]Hassan SZ, Ahmad K, Hicks S, Halvorsen P, Al-fuqaha A, Conci N, et al. Visual sentiment analysis from disaster images in social media. Sensors. 2022; 22(10):1-18.

[26]Kotha S, Haridasan S, Rattani A, Bowen A, Rimmington G, Dutta A. Multimodal combination of text and image tweets for disaster response assessment. International Workshop on Data-driven Resilience Research 2022 (pp. 1-10).

[27]Dong J, Wang W, Tan T. Casia image tampering detection evaluation database. In China summit and international conference on signal and information processing 2013 (pp. 422-6). IEEE.

[28]Hsu YF, Chang SF. Detecting image splicing using geometry invariants and camera characteristics consistency. In international conference on multimedia and explore 2006 (pp. 549-52). IEEE.

[29]Amerini I, Ballan L, Caldelli R, Del BA, Del TL, Serra G. Copy-move forgery detection and localization by means of robust clustering with J-linkage. Signal Processing: Image Communication. 2013; 28(6):659-69.

[30]Tralic D, Zupancic I, Grgic S, Grgic M. CoMoFoD-new database for copy-move forgery detection. In proceedings ELMAR 2013 (pp. 49-54). IEEE.

[31]Hakimi F, Hariri M, Gharehbaghi F. Image splicing forgery detection using local binary pattern and discrete wavelet transform. In 2nd international conference on knowledge-based engineering and innovation 2015 (pp. 1074-7). IEEE.

[32]Kaur M, Gupta S. A passive blind approach for image splicing detection based on DWT and LBP histograms. In 4th international symposium security in computing and communications 2016 (pp. 318-27). Springer Singapore.

[33]Hayat K, Qazi T. Forgery detection in digital images via discrete wavelet and discrete cosine transforms. Computers & Electrical Engineering. 2017; 62:448-58.

[34]Shah A, El-alfy ES. Image splicing forgery detection using DCT coefficients with multi-scale LBP. In international conference on computing sciences and engineering 2018 (pp. 1-6). IEEE.

[35]Parnak A, Baleghi Y, Kazemitabar J. A novel forgery detection algorithm based on mantissa distribution in digital images. In 6th Iranian conference on signal processing and intelligent systems 2020 (pp. 1-4). IEEE.

[36]Alkawaz MH, Sulong G, Saba T, Rehman A. Detection of copy-move image forgery based on discrete cosine transform. Neural Computing and Applications. 2018; 30:183-92.

[37]Islam MM, Karmakar G, Kamruzzaman J, Murshed M. A robust forgery detection method for copy–move and splicing attacks in images. Electronics. 2020; 9(9):1-22.

[38]Dua S, Singh J, Parthasarathy H. Image forgery detection based on statistical features of block DCT coefficients. Procedia Computer Science. 2020; 171:369-78.

[39]Xiao B, Wei Y, Bi X, Li W, Ma J. Image splicing forgery detection combining coarse to refined convolutional neural network and adaptive clustering. Information Sciences. 2020; 511:172-91.

[40]Qazi EU, Zia T, Almorjan A. Deep learning-based digital image forgery detection system. Applied Sciences. 2022; 12(6):1-17.

[41]Abdalla Y, Iqbal MT, Shehata M. Copy-move forgery detection and localization using a generative adversarial network and convolutional neural-network. Information. 2019; 10(9):1-26.

[42]Goel N, Kaur S, Bala R. Dual branch convolutional neural network for copy move forgery detection. IET Image Processing. 2021; 15(3):656-65.

[43]Ding H, Chen L, Tao Q, Fu Z, Dong L, Cui X. DCU-Net: a dual-channel U-shaped network for image splicing forgery detection. Neural Computing and Applications. 2023; 35(7):5015-31.

[44]Walia S, Kumar K, Kumar M, Gao XZ. Fusion of handcrafted and deep features for forgery detection in digital images. IEEE Access. 2021; 9:99742-55.

[45]Sabeena M, Abraham L. Convolutional block attention based network for copy-move image forgery detection. Multimedia Tools and Applications. 2024; 83(1):2383-405.

[46]Vijayalakshmi KNV, Sasikala J, Shanmuganathan C. Copy-paste forgery detection using deep learning with error level analysis. Multimedia Tools and Applications. 2024; 83(2):3425-49.

[47]Ali SS, Ganapathi II, Vu NS, Ali SD, Saxena N, Werghi N. Image forgery detection using deep learning by recompressing images. Electronics. 2022; 11(3):1-17.

[48]Martinez-cantin R. Bayesopt: a bayesian optimization library for nonlinear optimization, experimental design and bandits. Journal of Machine Learning Research. 2014; 15(1):3735-9.