相关论文: Code Membership Inference for Detecting Unauthoriz…

How can we verify whether copyrighted content was used to train a large vision-language model (VLM) without direct access to its training data? Motivated by the hypothesis that a VLM is able to recognize images from its training corpus, we…

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…

The security of code generated by large language models (LLMs) is a significant concern, as studies indicate that such code often contains vulnerabilities and lacks essential defensive programming constructs. This work focuses on examining…

How can we detect if copyrighted content was used in the training process of a language model, considering that the training data is typically undisclosed? We are motivated by the premise that a language model is likely to identify verbatim…

Fuzzing is an important dynamic program analysis technique designed for finding vulnerabilities in complex software. Fuzzing involves presenting a target program with crafted malicious input to cause crashes, buffer overflows, memory…

Machine learning as a service (MLaaS), and algorithm marketplaces are on a rise. Data holders can easily train complex models on their data using third party provided learning codes. Training accurate ML models requires massive labeled data…

Large Language Models (LLMs) have been widely used to automate programming tasks. Their capabilities have been evaluated by assessing the quality of generated code through tests or proofs. The extent to which they can reason about code is a…

Efficiency and safety of Large Language Models (LLMs), among other factors, rely on the quality of tokenization. A good tokenizer not only improves inference speed and language understanding but also provides extra defense against jailbreak…

Recent research has explored the creation of questions from code submitted by students. These Questions about Learners' Code (QLCs) are created through program analysis, exploring execution paths, and then creating code comprehension…

Large Language Models (LLMs) such as OpenAI Codex are increasingly being used as AI-based coding assistants. Understanding the impact of these tools on developers' code is paramount, especially as recent work showed that LLMs may suggest…

Pre-trained language models for code (PLMCs) have gained attention in recent research. These models are pre-trained on large-scale datasets using multi-modal objectives. However, fine-tuning them requires extensive supervision and is…

Does the training of large language models potentially infringe upon code licenses? Furthermore, are there any datasets available that can be safely used for training these models without violating such licenses? In our study, we assess the…

Large language models (LLMs) learn a vast amount of knowledge during pretraining, but they are often oblivious to the source(s) of such knowledge. We investigate the problem of intrinsic source citation, where LLMs are required to cite the…

In the era of large language models (LLMs), detecting pretraining data has been increasingly important due to concerns about fair evaluation and ethical risks. Current methods differentiate members and non-members by designing scoring…

Binary decompilation plays a vital role in various cybersecurity and software engineering tasks. Recently, end-to-end decompilation methods powered by large language models (LLMs) have garnered significant attention due to their ability to…

Code-mixing and code-switching (CSW) remain challenging phenomena for large language models (LLMs). Despite recent advances in multilingual modeling, LLMs often struggle in mixed-language settings, exhibiting systematic degradation in…

Large Language Models have received significant attention due to their abilities to solve a wide range of complex tasks. However these models memorize a significant proportion of their training data, posing a serious threat when disclosed…

The high cost of model training makes it increasingly desirable to develop techniques for unlearning. These techniques seek to remove the influence of a training example without having to retrain the model from scratch. Intuitively, once a…

Code pre-trained models (CodePTMs) have recently demonstrated significant success in code intelligence. To interpret these models, some probing methods have been applied. However, these methods fail to consider the inherent characteristics…

The training data in large language models is key to their success, but it also presents privacy and security risks, as it may contain sensitive information. Detecting pre-training data is crucial for mitigating these concerns. Existing…