相关论文: How Do Document Parsers Break? Auditing Structural…

Visual Document Understanding (VDU) systems have achieved strong performance in information extraction by integrating textual, layout, and visual signals. However, their robustness under realistic adversarial perturbations remains…

Programming-based Pre-trained Language Models (PPLMs) such as CodeBERT have achieved great success in many downstream code-related tasks. Since the memory and computational complexity of self-attention in the Transformer grow quadratically…

Humans can learn to solve new tasks by inducing high-level strategies from example solutions to similar problems and then adapting these strategies to solve unseen problems. Can we use large language models to induce such high-level…

Large language models (LLMs) are increasingly deployed in security-sensitive applications, yet remain vulnerable to backdoor attacks. However, existing backdoor defenses are difficult to operationalize for Backdoor Defense-as-a-Service…

Structured extraction with LLMs fails in production not because models lack understanding, but because output formatting is unreliable across models and prompts. A prompt that returns clean JSON on GPT-4 may produce fenced, prose-wrapped,…

We introduce OfficeQA Pro, a benchmark for evaluating AI agents on grounded, multi-document reasoning over a large and heterogeneous document corpus. The corpus consists of U.S. Treasury Bulletins spanning nearly 100 years, comprising…

Signature-based Intrusion Detection System (SIDS) provides a promising solution to the problem of web application security. However, the performance of the system highly relies on the quality of the signatures designed to detect attacks. A…

A central requirement of the European Union's Digital Services Act (DSA) is that online platforms undergo internal and external audits. A key component of these audits is the assessment of systemic risks, including the dissemination of…

As the use of deep learning in high impact domains becomes ubiquitous, it is increasingly important to assess the resilience of models. One such high impact domain is that of face recognition, with real world applications involving images…

Low rank adaptation (LoRA) has emerged as a prominent technique for fine-tuning large language models (LLMs) thanks to its superb efficiency gains over previous methods. While extensive studies have examined the performance and structural…

Large Language Models (LLMs) are being extensively used for cybersecurity purposes. One of them is the detection of vulnerable codes. For the sake of efficiency and effectiveness, compression and fine-tuning techniques are being developed,…

Libraries of Low-Rank Adaptation (LoRA) adapters are becoming a practical by-product of parameter-efficient adaptation. Once such adapters accumulate, a natural question is no longer how to train one adapter for one task, but how to reuse…

Though many deep learning (DL)-based vulnerability detection approaches have been proposed and indeed achieved remarkable performance, they still have limitations in the generalization as well as the practical usage. More precisely,…

Content Warning: This paper may contain unsafe or harmful content generated by LLMs that may be offensive to readers. Large Language Models (LLMs) increasingly serve as tooling platforms through structured output APIs, but the…

Despite their cultural and historical significance, Black digital archives continue to be a structurally underrepresented area in AI research and infrastructure. This is especially evident in efforts to digitize historical Black newspapers,…

The pervasive nature of software vulnerabilities has emerged as a primary factor for the surge in cyberattacks. Traditional vulnerability detection methods, including rule-based, signature-based, manual review, static, and dynamic analysis,…

Surface cracks are a very common indicator of potential structural faults. Their early detection and monitoring is an important factor in structural health monitoring. Left untreated, they can grow in size over time and require expensive…

Software supply chain attacks have revealed blind spots in existing SCA tools, which are often limited to a single ecosystem and assess either software artifacts or community activity in isolation. This fragmentation across tools and…

Retrieval Augmented Generation (RAG) frameworks improve the accuracy of large language models (LLMs) by integrating external knowledge from retrieved documents, thereby overcoming the limitations of models' static intrinsic knowledge.…

Latent Semantic Analysis (LSA) is a well known method for information retrieval. It has also been applied as a model of cognitive processing and word-meaning acquisition. This dual importance of LSA derives from its capacity to modulate the…