Emerging Concern of Scientific Fraud: Deep Learning and Image Manipulation

Qi, C.; Zhang, J.; Luo, P.

doi:10.1101/2020.11.24.395319

Home/Archive/bioRxiv

bioRxiv · 10.1101/2020.11.24.395319

Emerging Concern of Scientific Fraud: Deep Learning and Image Manipulation

Qi, C.·Zhang, J.·Luo, P.

View original source ↗Export metadata ↓

Abstract

Scientific fraud by image duplications and manipulations within western blot images is a rising problem. Currently, problematic western blot images are mainly detected by checking repeated bands or through visual observation. However, the completeness of the above methods in detecting problematic images has not been demonstrated. Here we show that Generative Adversarial Nets (GANs) can generate realistic western blot images that indistinguishable from real western blots. The overall accuracy of researchers for identifying synthetic western blot images is 0.52, which almost equal to blind guess (0.5). We found that GANs can generate western blot images with bands of the expected lengths, widths, and angles in desired positions that can fool researchers. For the case study, we find that the accuracy of detecting the synthetic western blot images is related to years of researchers performed studies relevant to western blots, but there was no apparent difference in accuracy among researchers with different academic degrees. Our results demonstrate that GANs can generate fake western blot images to fool existing problematic image detection methods. Therefore, more information is needed to ensure that the western blots appearing in scientific articles are real. We argue to require every western blot image to be uploaded along with a unique identifier generated by the laboratory machine and to peer review these images along with the corresponding submitted articles, which may reduce the incidence of scientific fraud.

Explore related subjects

scientific communication and education Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Qi, C., Zhang, J., Luo, P.. 2020-11-24. Emerging Concern of Scientific Fraud: Deep Learning and Image Manipulation. https://doi.org/10.1101/2020.11.24.395319

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Evaluating Large Language Models as Tools to Navigate Researchers in Rapidly Evolving Research Landscapes: A Case Study in Cancer Drug Response Prediction

Large Language Models (LLMs) have emerged as promising tools for assisting researchers in automating and accelerating the synthesis of literature reviews. However, their reliability is a significant concern due to issues like factual inaccuracies and hallucinations. The key question is whether LLMs can reliably provide comprehensive, up-to-date overviews and analyses. This study evaluates the performance of three leading LLMs (OpenAI's ChatGPT, Google's Gemini, and DeepSeek) on the complex task of generating a comprehensive survey paper on deep learning for cancer Drug Response Prediction (DRP). By testing both standard and Deep Research (DR) / Deep Think (DT) modes of LLMs with prompts of varying detail, this paper assesses key academic dimensions, including reference management, content quality, and analytical depth. Key findings reveal that while DR modes of LLMs significantly improve reliability by eliminating hallucinations, performance variations exist across models and prompts. A trade-off between reference quantity and integration quality was observed, and even the best-performing models lacked the analytical depth of human experts, often requiring extensive human supervision. The study concludes that LLMs currently serve as powerful assistive tools but still cannot replace the critical validation and synthesis provided by human researchers. Choosing the best LLM to use depends on the task in hand, while several strategies can be implemented to improve the produced output.

scientific communication and education↗

bioRxiv2021

Inferring livestock movement networks from archived data to support infectious disease control in developing countries

The use of network analysis to support livestock disease control in low middle-income countries (LMICs) has historically been hampered by the cost of generating empirical data in the absence of animal movement recording schemes. To fill this gap, methods which exploit freely available demographic and archived molecular data can be used to generate livestock networks based on gravity and phylogeographic modelling techniques, respectively. However, questions remain on the performance of these methods in capturing the topology of empirical networks. Here, we compare output from these network methodologies to a network constructed from either empirical data or randomly generated data. To facilitate this comparison, the spread of infectious diseases was simulated, it is this evaluation that demonstrates their potential utility to inform robust livestock disease control strategies. The molecular network was the closest approximation to the empirical network, both in relation to topological and epidemic characteristics, whereas size of epidemics in the gravity network tended to be larger, better agreement across all three networks was observed when; a) total nodes infected, b) percentage infection take off were compared. These methods consistently identified the same important animal movement and trade hotspots as the empirical networks. We therefore consider this proof-of-concept that demographic data such as censuses and archived molecular data could be repurposed to inform livestock disease management in LMICs. Author summaryLive animal movements in Africa represent a significant risk of transmission and spread of infectious diseases in livestock populations, and therefore, have direct implications on the food security of the continent. Here we explore the potential utility of available data to support control strategies, by comparing movement networks inferred from such data i.e. census and pathogen molecular data using gravity modelling and phylogeography respectively. Their utility is evaluated by comparing their topology and disease spread characteristics to empirical live animal movement. Based on our results, we posit that archived data can be repurposed to support infectious disease control on the African continent.

scientific communication and education↗

bioRxiv2021

scite: a smart citation index that displays the context of citations and classifies their intent using deep learning

Citation indices are tools used by the academic community for research and research evaluation which aggregate scientific literature output and measure scientific impact by collating citation counts. Citation indices help measure the interconnections between scientific papers but fall short because they only display paper titles, authors, and the date of publications, and fail to communicate contextual information about why a citation was made. The usage of citations in research evaluation without due consideration to context can be problematic, if only because a citation that disputes a paper is treated the same as a citation that supports it. To solve this problem, we have used machine learning and other techniques to develop a "smart citation index" called scite, which categorizes citations based on context. Scite shows how a citation was used by displaying the surrounding textual context from the citing paper, and a classification from our deep learning model that indicates whether the statement provides supporting or disputing evidence for a referenced work, or simply mentions it. Scite has been developed by analyzing over 23 million full-text scientific articles and currently has a database of more than 800 million classified citation statements. Here we describe how scite works and how it can be used to further research and research evaluation.

scientific communication and education↗