Related papers: DVD: A Robust Method for Detecting Variant Contami…

Large Language Models (LLMs) have showcased their remarkable capabilities in diverse domains, encompassing natural language understanding, translation, and even code generation. The potential for LLMs to generate harmful content is a…

Benchmarks like GSM8K are popular measures of mathematical reasoning, but leaderboard gains can overstate true capability due to memorization of fixed test sets. Most robustness variants apply surface-level perturbations (paraphrases,…

Code vulnerability detection (CVD) is essential for addressing and preventing system security issues, playing a crucial role in ensuring software security. Previous learning-based vulnerability detection methods rely on either fine-tuning…

Deep learning-based approaches, particularly those leveraging pre-trained language models (PLMs), have shown promise in automated software vulnerability detection. However, existing methods are predominantly limited to specific programming…

Large Language Models (LLMs) changed the way we design and interact with software systems. Their ability to process and extract information from text has drastically improved productivity in a number of routine tasks. Developers that want…

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

Large language models (LLMs) are known to be trained on vast amounts of data, which may unintentionally or intentionally include data from commonly used benchmarks. This inclusion can lead to cheatingly high scores on model leaderboards,…

Diffusion Transformers (DiT) trained with flow matching in a VAE latent space have unified visual generation across images and videos. A natural next step toward a single architecture for both generation (visual synthesis) and understanding…

Large Language Models (LLMs) are rapidly becoming commodity components of larger software systems. This poses natural security and privacy problems: poisoned data retrieved from one component can change the model's behavior and compromise…

Dataset distillation (DD) aims to synthesize compact training sets that enable models to achieve high accuracy with significantly fewer samples. Recent diffusion-based DD methods commonly introduce semantic guidance through late-stage…

Autoregressive language models (ARMs) have been shown to memorize and occasionally reproduce training data verbatim, raising concerns about privacy and copyright liability. Diffusion language models (DLMs) have recently emerged as a…

This dissertation presents an evaluation of several language models on software defect datasets. A language Model (LM) "can provide word representation and probability indication of word sequences as the core component of an NLP system."…

Data contamination in model evaluation has become increasingly prevalent with the growing popularity of large language models. It allows models to "cheat" via memorisation instead of displaying true capabilities. Therefore, contamination…

Large Language Models (LLMs) frequently memorize long sequences verbatim, often with serious legal and privacy implications. Much prior work has studied such verbatim memorization using observational data. To complement such work, we…

Lemmatization is the task of transforming all words in a given text to their dictionary forms. While large language models (LLMs) have demonstrated their ability to achieve competitive results across a wide range of NLP tasks, there is no…

Malware authors have traditionally relied on polymorphic techniques to produce variants in the same malware family, complicating signature-based detection. Integrating generative AI into offensive toolchains enables attackers to synthesize…

Large Language Models (LLMs) have been recently proposed for supporting domain modeling tasks mostly related to the completion of partial models by recommending additional model elements. However, there are many more modeling tasks, one of…

Deep learning malware detectors achieve high classification accuracy but suffer from severe interpretability limitations, typically returning probabilistic verdicts that lack forensic context. We introduce AsmRAG, a framework performing…

Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-trivial reasoning about program semantics. Finding training examples to teach LLMs to solve these…

Large language models (LLMs) can be used to generate text data for training and evaluating other models. However, creating high-quality datasets with LLMs can be challenging. In this work, we explore human-AI partnerships to facilitate high…