In the age of powerful AI-generated text, automatic detectors have emerged to identify machine-written content. This poses a threat to author privacy and freedom, as text authored with AI assistance may be unfairly flagged. We propose AuthorMist, a novel reinforcement learning-based system to transform AI-generated text into human-like writing. AuthorMist leverages a 3-billion-parameter language model as a backbone, fine-tuned with Group Relative Policy Optimization (GPRO) to paraphrase text in a way that evades AI detectors. Our framework establishes a generic approach where external detector APIs (GPTZero, WinstonAI, Originality.ai, etc.) serve as reward functions within the reinforcement learning loop, enabling the model to systematically learn outputs that these detectors are less likely to classify as AI-generated. This API-as-reward methodology can be applied broadly to optimize text against any detector with an accessible interface. Experiments on multiple datasets and detectors demonstrate that AuthorMist effectively reduces the detectability of AI-generated text while preserving the original meaning. Our evaluation shows attack success rates ranging from 78.6% to 96.2% against individual detectors, significantly outperforming baseline paraphrasing methods. AuthorMist maintains high semantic similarity (above 0.94) with the original text while successfully evading detection. These results highlight limitations in current AI text detection technologies and raise questions about the sustainability of the detection-evasion arms race.

This paper presents a dynamic, real-time approach to detecting anomalous blockchain transactions. The proposed tool, BlockGPT, generates tracing representations of blockchain activity and trains from scratch a large language model to act as a real-time Intrusion Detection System. Unlike traditional methods, BlockGPT is designed to offer an unrestricted search space and does not rely on predefined rules or patterns, enabling it to detect a broader range of anomalies. We demonstrate the effectiveness of BlockGPT through its use as an anomaly detection tool for Ethereum transactions. In our experiments, it effectively identifies abnormal transactions among a dataset of 68M transactions and has a batched throughput of 2284 transactions per second on average. Our results show that, BlockGPT identifies abnormal transactions by ranking 49 out of 124 attacks among the top-3 most abnormal transactions interacting with their victim contracts. This work makes contributions to the field of blockchain transaction analysis by introducing a custom data encoding compatible with the transformer architecture, a domain-specific tokenization technique, and a tree encoding method specifically crafted for the Ethereum Virtual Machine (EVM) trace representation.

Forecasting Financial Time Series (FTS) has been of interest to financial market participants who are interested in making profitable trades on the financial markets. It has historically been approached using stochastic and machine learning models. Stochastic methods include linear models such as Autoregressive Integrated Moving Average (ARIMA) [1] that support non-stationary time series and non-linear models, including the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) [2] model. Machine learning methods are data-driven approaches, among which Recurrent Neural Networks (RNNs) [3], more specifically, Long Short-Term Memory (LSTM) networks [4], have been especially popular for time series prediction. Periodically, new deep learning models are being adopted in quantitative research to find the most accurate models in FTS forecasting that would lead to more efficient trading strategies. Recently, a new type of deep learning [5] architecture called Transformer [6], relying on Attention [7], was introduced for Natural Language Processing (NLP) applications. Transformers have since been used in other applications such as computer vision tasks [8] and more recently in time series forecasting. This paper will focus on the application of Transformers in high-frequency FTS forecasting. FTS are characterized by properties including frequency, auto-correlation, heteroskedasticity, drift, and seasonality [9].