As social media continues to grow rapidly, the prevalence of harassment on these platforms has also increased. This has piqued the interest of researchers in the field of fake detection. Social media data, often forms complex graphs with numerous nodes, posing several challenges. These challenges and limitations include dealing with a significant amount of irrelevant features in matrices and addressing issues such as high data dispersion and an imbalanced class distribution within the dataset. To overcome these challenges and limitations, researchers have employed auto-encoders and a combination of semi-supervised learning with a GAN algorithm, referred to as SGAN. Our proposed method utilizes auto-encoders for feature extraction and incorporates SGAN. By leveraging an unlabeled dataset, the unsupervised layer of SGAN compensates for the limited availability of labeled data, making efficient use of the limited number of labeled instances. Multiple evaluation metrics were employed, including the Confusion Matrix and the ROC curve. The dataset was divided into training and testing sets, with 100 labeled samples for training and 1,000 samples for testing. The novelty of our research lies in applying SGAN to address the issue of imbalanced datasets in fake account detection. By optimizing the use of a smaller number of labeled instances and reducing the need for extensive computational power, our method offers a more efficient solution. Additionally, our study contributes to the field by achieving an 81% accuracy in detecting fake accounts using only 100 labeled samples. This demonstrates the potential of SGAN as a powerful tool for handling minority classes and addressing big data challenges in fake account detection.

Although extensive research has been carried out to evaluate the effectiveness of AI tools and models in detecting deep fakes, the question remains unanswered regarding whether these models can accurately identify genuine images that appear artificial. In this study, as an initial step towards addressing this issue, we have curated a dataset of 510 genuine images that exhibit a fake appearance and conducted an assessment using two AI models. We show that two models exhibited subpar performance when applied to our dataset. Additionally, our dataset can serve as a valuable tool for assessing the ability of deep learning models to comprehend complex visual stimuli. We anticipate that this research will stimulate further discussions and investigations in this area. Our dataset is accessible at https://github.com/aliborji/FLORIDA.

The self-attention revolution allowed generative language models to scale and achieve increasingly impressive abilities. Such models - commonly referred to as Large Language Models (LLMs) - have recently gained prominence with the general public, thanks to conversational fine-tuning, putting their behavior in line with public expectations regarding AI. This prominence amplified prior concerns regarding the misuse of LLMs and led to the emergence of numerous tools to detect LLMs in the wild. Unfortunately, most such tools are critically flawed. While major publications in the LLM detectability field suggested that LLMs were easy to detect with fine-tuned autoencoders, the limitations of their results are easy to overlook. Specifically, they assumed publicly available generative models without fine-tunes or non-trivial prompts. While the importance of these assumptions has been demonstrated, until now, it remained unclear how well such detection could be countered. Here, we show that an attacker with access to such detectors' reference human texts and output not only evades detection but can fully frustrate the detector training - with a reasonable budget and all its outputs labeled as such. Achieving it required combining common "reinforcement from critic" loss function modification and AdamW optimizer, which led to surprisingly good fine-tuning generalization. Finally, we warn against the temptation to transpose the conclusions obtained in RNN-driven text GANs to LLMs due to their better representative ability. These results have critical implications for the detection and prevention of malicious use of generative language models, and we hope they will aid the designers of generative models and detectors.

Counterfeiters have leveraged consumer fear and uncertainty created by coronavirus (COVID-19) to flood the market with fakes, misinformation and counterfeits, taking advantage of demand and panic buying for essential goods and services. As one example, social media bot accounts are causing life-threatening coronavirus misinformation to spread across the internet. The Reuters Institute for the Study of Journalism and the Oxford Internet Institute recently released the results of a study that reviewed 225 pieces of COVID-19 misinformation rated false or misleading by fact-checkers. The research found that "false (COVID-19) information spread by politicians, celebrities, and other prominent public figures" accounted for 69% of total engagement on social media, even though their posts made up just 20% of the study's sample. Likewise, counterfeit N95 masks, test kits and ventilator parts have posed challenges for governments across the globe trying to keep their populations safe during COVID-19.