相关论文: DeepIaC: Deep Learning-Based Linguistic Anti-patte…

Realizing flow security in a concurrent environment is extremely challenging, primarily due to non-deterministic nature of execution. The difficulty is further exacerbated from a security angle if sequential threads disclose control…

Logical anomalies are violations of predefined constraints on object quantity, spatial layout, and compositional relationships in industrial images. While prior work largely treats anomaly detection as a binary decision, such formulations…

Ensuring the security of critical infrastructure has become increasingly vital with the proliferation of Internet of Things (IoT) systems. However, the heterogeneous nature of IoT data and the lack of human-comprehensible insights from…

This study utilizes Independent Component Analysis (ICA) to unveil a consistent semantic structure within embeddings of words or images. Our approach extracts independent semantic components from the embeddings of a pre-trained model by…

Methods for combining predictions from different models in a supervised learning setting must somehow estimate/predict the quality of a model's predictions at unknown future inputs. Many of these methods (often implicitly) make the…

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."…

Log files record computational events that reflect system state and behavior, making them a primary source of operational insights in modern computer systems. Automated anomaly detection on logs is therefore critical, yet most established…

An intriguing property of deep neural networks is their inherent vulnerability to adversarial inputs, which significantly hinders their application in security-critical domains. Most existing detection methods attempt to use carefully…

Current techniques for detecting AI-generated text are largely confined to manual feature crafting and supervised binary classification paradigms. These methodologies typically lead to performance bottlenecks and unsatisfactory…

Code Large Language Models (LLMs) demonstrate great versatility in adapting to various downstream tasks, including code generation and completion, as well as bug detection and fixing. However, Code LLMs often fail to capture existing coding…

Machine unlearning aims to remove the influence of specific data from trained language models. In real-world deployments, unlearning requests often arrive sequentially, which challenges existing fine-tuning-based methods: fine-tuning each…

Machine Learning-as-a-Service systems (MLaaS) have been largely developed for cybersecurity-critical applications, such as detecting network intrusions and fake news campaigns. Despite effectiveness, their robustness against adversarial…

Producing high-quality code is essential as it makes a codebase more maintainable, reducing the cost and effort associated with a project. However, students learning to program are often given short, automatically graded programming tasks…

As large language models become components of larger agentic systems, evaluation reliability becomes critical: unreliable sub-agents introduce brittleness into downstream system behavior. Yet current evaluation practice, reporting a single…

Despite explicit alignment efforts for large language models (LLMs), they can still be exploited to trigger unintended behaviors, a phenomenon known as "jailbreaking." Current jailbreak attack methods mainly focus on discrete prompt…

Code generation with Large Language Models (LLMs) has helped to increase software developer productivity in coding tasks, but has yet to have significant impact on the tasks of software developers that surround this code. In particular, the…

Differential testing can be an effective way to find bugs in software systems with multiple implementations that conform to the same specification, like compilers, network protocol parsers, or language runtimes. Specifications for such…

Detecting problematic content, such as hate speech, is a multifaceted and ever-changing task, influenced by social dynamics, user populations, diversity of sources, and evolving language. There has been significant efforts, both in academia…

Although AI drafting tools have gained prominence in patent writing, the systematic evaluation of AI-generated patent content quality represents a significant research gap. To address this gap, We propose to evaluate patents using…

High-performance computing systems (HPC) provide powerful capabilities for modeling, simulation, and data analytics for a broad class of computational problems. They enable extreme performance of the order of quadrillion floating-point…