Weidong Shi

Rabimba Karanjai, Edward Li, Lei Xu et al.

The introduction of large language models (LLMs) like ChatGPT and Google Palm2 for smart contract generation seems to be the first well-established instance of an AI pair programmer. LLMs have access to a large number of open-source smart contracts, enabling them to utilize more extensive code in Solidity than other code generation tools. Although the initial and informal assessments of LLMs for smart contract generation are promising, a systematic evaluation is needed to explore the limits and benefits of these models. The main objective of this study is to assess the quality of generated code provided by LLMs for smart contracts. We also aim to evaluate the impact of the quality and variety of input parameters fed to LLMs. To achieve this aim, we created an experimental setup for evaluating the generated code in terms of validity, correctness, and efficiency. Our study finds crucial evidence of security bugs getting introduced in the generated smart contracts as well as the overall quality and correctness of the code getting impacted. However, we also identified the areas where it can be improved. The paper also proposes several potential research directions to improve the process, quality and safety of generated smart contract codes.

Yang Lu, Rabimba Karanjai, Lei Xu et al.

AI research pipelines now produce a growing share of publishable academic output, including work that meets existing peer-review standards for quality and novelty. Yet the publication system was built on the assumption of universal human authorship and lacks a principled way to evaluate knowledge produced through automated pipelines. This paper proposes a two-layer certification framework that separates knowledge quality assessment from grading of human contribution, allowing publication systems to handle pipeline-generated work consistently and transparently without creating new institutions. The paper uses normative-conceptual analysis, framework design under four explicit constraints, and dry-run validation on two representative submission cases spanning key attribution scenarios. The framework grades contributions as Category A (pipeline-reachable), Category B (requiring human direction at identifiable stages), and Category C (beyond current pipeline reach at the formulation stage). It also introduces benchmark slots for fully disclosed automated research as both a transparent publication track and a calibration instrument for reviewer judgment. Contribution grading is contemporaneous, based on pipeline capability at the time of submission. Dry-run validation shows that the framework can certify knowledge appropriately while tolerating irreducible attribution uncertainty. The paper argues that publication has always certified both that knowledge is valid and that a human made it. AI pipelines separate these functions for the first time. The framework is implementable within existing editorial infrastructure and grounds recognition of frontier human contribution in epistemic achievement rather than unverifiable claims of human origin.

Rabimba Karanjai, Boris Shor, Amanda Austin et al.

This paper investigates the use of Large Language Models (LLMs) to synthesize public opinion data, addressing challenges in traditional survey methods like declining response rates and non-response bias. We introduce a novel technique: role creation based on knowledge injection, a form of in-context learning that leverages RAG and specified personality profiles from the HEXACO model and demographic information, and uses that for dynamically generated prompts. This method allows LLMs to simulate diverse opinions more accurately than existing prompt engineering approaches. We compare our results with pre-trained models with standard few-shot prompts. Experiments using questions from the Cooperative Election Study (CES) demonstrate that our role-creation approach significantly improves the alignment of LLM-generated opinions with real-world human survey responses, increasing answer adherence. In addition, we discuss challenges, limitations and future research directions.

Rabimba Karanjai, Lei Xu, Weidong Shi

The rapid growth of the blockchain ecosystem and the increasing value locked in smart contracts necessitate robust security measures. While languages like Solidity and Move aim to improve smart contract security, vulnerabilities persist. This paper presents Smartify, a novel multi-agent framework leveraging Large Language Models (LLMs) to automatically detect and repair vulnerabilities in Solidity and Move smart contracts. Unlike traditional methods that rely solely on vast pre-training datasets, Smartify employs a team of specialized agents working on different specially fine-tuned LLMs to analyze code based on underlying programming concepts and language-specific security principles. We evaluated Smartify on a dataset for Solidity and a curated dataset for Move, demonstrating its effectiveness in fixing a wide range of vulnerabilities. Our results show that Smartify (Gemma2+codegemma) achieves state-of-the-art performance, surpassing existing LLMs and enhancing general-purpose models' capabilities, such as Llama 3.1. Notably, Smartify can incorporate language-specific knowledge, such as the nuances of Move, without requiring massive language-specific pre-training datasets. This work offers a detailed analysis of various LLMs' performance on smart contract repair, highlighting the strengths of our multi-agent approach and providing a blueprint for developing more secure and reliable decentralized applications in the growing blockchain landscape. We also provide a detailed recipe for extending this to other similar use cases.

Dana Alsagheer, Yang Lu, Abdulrahman Kamal et al.

Recent advancements in Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains. However, effective decision-making relies heavily on strong reasoning abilities. Reasoning is the foundation for decision-making, providing the analytical and logical framework to make sound choices. Reasoning involves analyzing information, drawing inferences, and reaching conclusions based on logic or evidence. Decision-making builds on this foundation by applying the insights from reasoning to select the best course of action among alternatives. Together, these processes create a continuous cycle of thought and action aimed at achieving goals effectively. As AI technology evolves, there is a growing trend to train LLMs to excel in general reasoning. This study explores how the general reasoning capabilities of LLMs connect to their performance in domain-specific reasoning tasks.

Rabimba Karanjai, Weidong Shi

Artificial General Intelligence falls short when communicating role specific nuances to other systems. This is more pronounced when building autonomous LLM agents capable and designed to communicate with each other for real world problem solving. Humans can communicate context and domain specific nuances along with knowledge, and that has led to refinement of skills. In this work we propose and evaluate a novel method that leads to knowledge distillation among LLM agents leading to realtime human role play preserving unique contexts without relying on any stored data or pretraining. We also evaluate how our system performs better in simulated real world tasks compared to state of the art.

Hadi Mansourifar, Dana Alsagheer, Reza Fathi et al.

With the rise of voice chat rooms, a gigantic resource of data can be exposed to the research community for natural language processing tasks. Moderators in voice chat rooms actively monitor the discussions and remove the participants with offensive language. However, it makes the hate speech detection even more difficult since some participants try to find creative ways to articulate hate speech. This makes the hate speech detection challenging in new social media like Clubhouse. To the best of our knowledge all the hate speech datasets have been collected from text resources like Twitter. In this paper, we take the first step to collect a significant dataset from Clubhouse as the rising star in social media industry. We analyze the collected instances from statistical point of view using the Google Perspective Scores. Our experiments show that, the Perspective Scores can outperform Bag of Words and Word2Vec as high level text features.

Hadi Mansourifar, Dana Alsagheer, Weidong Shi et al.

Hate speech detection has become a hot topic in recent years due to the exponential growth of offensive language in social media. It has proven that, state-of-the-art hate speech classifiers are efficient only when tested on the data with the same feature distribution as training data. As a consequence, model architecture plays the second role to improve the current results. In such a diverse data distribution relying on low level features is the main cause of deficiency due to natural bias in data. That's why we need to use high level features to avoid a biased judgement. In this paper, we statistically analyze the Perspective Scores and their impact on hate speech detection. We show that, different hate speech datasets are very similar when it comes to extract their Perspective Scores. Eventually, we prove that, over-sampling the Perspective Scores of a hate speech dataset can significantly improve the generalization performance when it comes to be tested on other hate speech datasets.

Hadi Mansourifar, Weidong Shi

Virtual Big Data (VBD) proved to be effective to alleviate mode collapse and vanishing generator gradient as two major problems of Generative Adversarial Neural Networks (GANs) very recently. In this paper, we investigate the capability of VBD to address two other major challenges in Machine Learning including deep autoencoder training and imbalanced data classification. First, we prove that, VBD can significantly decrease the validation loss of autoencoders via providing them a huge diversified training data which is the key to reach better generalization to minimize the over-fitting problem. Second, we use the VBD to propose the first projection-based method called cross-concatenation to balance the skewed class distributions without over-sampling. We prove that, cross-concatenation can solve uncertainty problem of data driven methods for imbalanced classification.

Hadi Mansourifar, Weidong Shi

Rounding confidence score is considered trivial but a simple and effective countermeasure to stop gradient descent based image reconstruction attacks. However, its capability in the face of more sophisticated reconstruction attacks is an uninvestigated research area. In this paper, we prove that, the face reconstruction attacks based on composite faces can reveal the inefficiency of rounding policy as countermeasure. We assume that, the attacker takes advantage of face composite parts which helps the attacker to get access to the most important features of the face or decompose it to the independent segments. Afterwards, decomposed segments are exploited as search parameters to create a search path to reconstruct optimal face. Face composition parts enable the attacker to violate the privacy of face recognition models even with a blind search. However, we assume that, the attacker may take advantage of random search to reconstruct the target face faster. The algorithm is started with random composition of face parts as initial face and confidence score is considered as fitness value. Our experiments show that, since the rounding policy as countermeasure can't stop the random search process, current face recognition systems are extremely vulnerable against such sophisticated attacks. To address this problem, we successfully test Face Detection Score Filtering (FDSF) as a countermeasure to protect the privacy of training data against proposed attack.

Hadi Mansourifar, Weidong Shi

Fake face detection is a significant challenge for intelligent systems as generative models become more powerful every single day. As the quality of fake faces increases, the trained models become more and more inefficient to detect the novel fake faces, since the corresponding training data is considered outdated. In this case, robust One-Shot learning methods is more compatible with the requirements of changeable training data. In this paper, we propose a universal One-Shot GAN generated fake face detection method which can be used in significantly different areas of anomaly detection. The proposed method is based on extracting out-of-context objects from faces via scene understanding models. To do so, we use state of the art scene understanding and object detection methods as a pre-processing tool to detect the weird objects in the face. Second, we create a bag of words given all the detected out-of-context objects per all training data. This way, we transform each image into a sparse vector where each feature represents the confidence score related to each detected object in the image. Our experiments show that, we can discriminate fake faces from real ones in terms of out-of-context features. It means that, different sets of objects are detected in fake faces comparing to real ones when we analyze them with scene understanding and object detection models. We prove that, the proposed method can outperform previous methods based on our experiments on Style-GAN generated fake faces.

Hadi Mansourifar, Lin Chen, Weidong Shi

Increasingly growing Cryptocurrency markets have become a hive for scammers to run pump and dump schemes which is considered as an anomalous activity in exchange markets. Anomaly detection in time series is challenging since existing methods are not sufficient to detect the anomalies in all contexts. In this paper, we propose a novel hybrid pump and dump detection method based on distance and density metrics. First, we propose a novel automatic thresh-old setting method for distance-based anomaly detection. Second, we propose a novel metric called density score for density-based anomaly detection. Finally, we exploit the combination of density and distance metrics successfully as a hybrid approach. Our experiments show that, the proposed hybrid approach is reliable to detect the majority of alleged P & D activities in top ranked exchange pairs by outperforming both density-based and distance-based methods.

Lin Chen, Lei Xu, Zhimin Gao et al.

Recent advances in the blockchain research have been made in two important directions. One is refined resilience analysis utilizing game theory to study the consequences of selfish behaviors of users (miners), and the other is the extension from a linear (chain) structure to a non-linear (graphical) structure for performance improvements, such as IOTA and Graphcoin. The first question that comes to people's minds is what improvements that a blockchain system would see by leveraging these new advances. In this paper, we consider three major metrics for a blockchain system: full verification, scalability, and finality-duration. We { establish a formal framework and} prove that no blockchain system can achieve full verification, high scalability, and low finality-duration simultaneously. We observe that classical blockchain systems like Bitcoin achieves full verification and low finality-duration, Harmony and Ethereum 2.0 achieve low finality-duration and high scalability. As a complementary, we design a non-linear blockchain system that achieves full verification and scalability. We also establish, for the first time, the trade-off between scalability and finality-duration.

Lei Xu, Lin Chen, Zhimin Gao et al.

Public blockchains provide a decentralized method for storing transaction data and have many applications in different sectors. In order for users to track transactions, a simple method is to let them keep a local copy of the entire public ledger. Since the size of the ledger keeps growing, this method becomes increasingly less practical, especially for lightweight users such as IoT devices and smartphones. In order to cope with the problem, several solutions have been proposed to reduce the storage burden. However, existing solutions either achieve a limited storage reduction (e.g., simple payment verification), or rely on some strong security assumption (e.g., the use of trusted server). In this paper, we propose a new approach to solving the problem. Specifically, we propose an \underline{e}fficient verification protocol for \underline{p}ublic \underline{b}lock\underline{c}hains, or EPBC for short. EPBC is particularly suitable for lightweight users, who only need to store a small amount of data that is {\it independent of} the size of the blockchain. We analyze EPBC's performance and security, and discuss its integration with existing public ledger systems. Experimental results confirm that EPBC is practical for lightweight users.

Lin Chen, Lei Xu, Shouhuai Xu et al.

Bribery in election (or computational social choice in general) is an important problem that has received a considerable amount of attention. In the classic bribery problem, the briber (or attacker) bribes some voters in attempting to make the briber's designated candidate win an election. In this paper, we introduce a novel variant of the bribery problem, "Election with Bribed Voter Uncertainty" or BVU for short, accommodating the uncertainty that the vote of a bribed voter may or may not be counted. This uncertainty occurs either because a bribed voter may not cast its vote in fear of being caught, or because a bribed voter is indeed caught and therefore its vote is discarded. As a first step towards ultimately understanding and addressing this important problem, we show that it does not admit any multiplicative $O(1)$-approximation algorithm modulo standard complexity assumptions. We further show that there is an approximation algorithm that returns a solution with an additive-$ε$ error in FPT time for any fixed $ε$.