相关论文: Your Code Secret Belongs to Me: Neural Code Comple…

Emerging neural networks based machine learning techniques such as deep learning and its variants have shown tremendous potential in many application domains. However, they raise serious privacy concerns due to the risk of leakage of highly…

Mechanistic interpretability aspires to reverse-engineer neural networks into explicit algorithms, while model editing seeks to modify specific behaviours without retraining. Both areas are typically evaluated with informal evidence and…

Large Language Models (LLMs) have recently demonstrated remarkable performance in various Natural Language Processing (NLP) applications, such as sentiment analysis, content generation, and personalized recommendations. Despite their…

Despite the impressive capabilities of Large Language Models (LLMs) in various tasks, their vulnerability to unsafe prompts remains a critical issue. These prompts can lead LLMs to generate responses on illegal or sensitive topics, posing a…

The lack of transparency about code datasets used to train large language models (LLMs) makes it difficult to detect, evaluate, and mitigate data leakage. We present a perturbation-based method to quantify memorization advantage in code…

Recommender systems suffer from confounding biases when there exist confounders affecting both item features and user feedback (e.g., like or not). Existing causal recommendation methods typically assume confounders are fully observed and…

Developing secure smart contracts remains a challenging task. Existing approaches are either impractical or leave the burden to developers for fixing bugs. In this paper, we propose the first practical smart contract compiler, called HCC,…

Machine-learning (ML) shortcuts or spurious correlations are artifacts in datasets that lead to very good training and test performance but severely limit the model's generalization capability. Such shortcuts are insidious because they go…

Writing software exploits is an important practice for offensive security analysts to investigate and prevent attacks. In particular, shellcodes are especially time-consuming and a technical challenge, as they are written in assembly…

Fooling adversaries with traps such as honeytokens can slow down cyber attacks and create strong indicators of compromise. Unfortunately, cyber deception techniques are often poorly specified. Also, realistically measuring their…

Human capital (HC) is increasingly important to corporate value creation. Unlike other assets, however, HC is not currently subject to well-defined measurement or disclosure rules. We use a machine learning algorithm (word2vec) trained on a…

Deep learning has demonstrated great abilities in various code generation tasks. However, despite the great convenience for some developers, many are concerned that the code generators may recite or closely mimic copyrighted training data…

We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for training Large Language Models for coding. Existing…

Large language models (LLMs) have manifested strong ability to generate codes for productive activities. However, current benchmarks for code synthesis, such as HumanEval, MBPP, and DS-1000, are predominantly oriented towards introductory…

In the rapidly evolving field of machine learning, training models with datasets from various locations and organizations presents significant challenges due to privacy and legal concerns. The exploration of effective collaborative training…

Today, AI technology is showing its strengths in almost every industry and walks of life. From text generation, text summarization, chatbots, NLP is being used widely. One such paradigm is automatic code generation. An AI could be…

Model-sharing platforms, such as Hugging Face, ModelScope, and OpenCSG, have become central to modern machine learning development, enabling developers to share, load, and fine-tune pre-trained models with minimal effort. However, the…

Large Language Models (LLMs) have become powerful tools for automated code generation. However, these models often overlook critical security practices, which can result in the generation of insecure code that contains…

While large code language models have made significant strides in AI-assisted coding tasks, there are growing concerns about privacy challenges. The user code is transparent to the cloud LLM service provider, inducing risks of unauthorized…

Large language models (LLMs) for code completion and generation are increasingly used in software development, yet they may reproduce training examples verbatim and without authorship attribution, raising legal and ethical concerns around…