Related papers: AnonLFI 2.0: Extensible Architecture for PII Pseud…
The pretraining and fine-tuning approach has become the leading technique for various NLP applications. However, recent studies reveal that fine-tuning data, due to their sensitive nature, domain-specific characteristics, and…
Multimodal key information extraction (KIE) models have been studied extensively on semi-structured documents. However, their investigation on unstructured documents is an emerging research topic. The paper presents an approach to adapt a…
Physical unclonable functions (PUFs) exploit the intrinsic complexity and irreproducibility of physical systems to generate secret information. PUFs have the potential to provide fundamentally higher security than traditional cryptographic…
Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation. However, our research identifies a vulnerability: LLMs can be manipulated by…
Software obfuscation and encryption present persistent challenges for program comprehension and security analysis, particularly when adversaries conceal Indicators of Compromise (IoCs) such as IP addresses within source code. While Large…
The Domain Name System Security Extensions (DNSSEC) are critical for preventing DNS spoofing, yet its specifications contain ambiguities and vulnerabilities that elude traditional "break-and-fix" approaches. A holistic, foundational…
Artificial intelligence systems have achieved remarkable capability in natural language processing, perception and decision-making tasks. However, their behaviour often remains opaque and difficult to verify, limiting their applicability in…
Smart devices serviced by large-scale AI models necessitates user data transfer to the cloud for inference. For speech applications, this means transferring private user information, e.g., speaker identity. Our paper proposes a…
In an era where personal photos are easily leaked and collected, face de-identification is a crucial method for protecting identity privacy. However, current face de-identification techniques face challenges in preserving attribute details…
Current LLM-based frameworks for text anonymization usually rely on remote API services from powerful LLMs, which creates an inherent privacy paradox: users must disclose the raw data to untrusted third parties for guaranteed privacy…
Large language models (LLMs) inference is both expensive and slow. Local caching of responses offers a practical solution to reduce the cost and latency of LLM queries. In research contexts, caching also enhances reproducibility and…
The performance of spoofing countermeasure systems depends fundamentally upon the use of sufficiently representative training data. With this usually being limited, current solutions typically lack generalisation to attacks encountered in…
Modern LLMs are increasingly accessed via black-box APIs, requiring users to transmit sensitive prompts, outputs, and fine-tuning data to external providers, creating a critical privacy risk at the API boundary. We introduce AlienLM, a…
The Self-Sovereign Identity (SSI) paradigm is instrumental for decentralised identity management, allowing an entity to create, manage, and present their digital credentials without relying on centralised authorities. Credential selective…
We present new schemes for solving prefix authentication and secure relative timestamping. By casting a new light on antimonotone linking schemes, we improve upon the state of the art in prefix authentication, and in timestamping with…
Optical Character Recognition (OCR) systems have been widely used in various of application scenarios. Designing an OCR system is still a challenging task. In previous work, we proposed a practical ultra lightweight OCR system (PP-OCR) to…
As the number and sophistication of cyber attacks have increased, threat hunting has become a critical aspect of active security, enabling proactive detection and mitigation of threats before they cause significant harm. Open-source cyber…
Extracting structured intelligence via Named Entity Recognition (NER) is critical for cybersecurity, but the proliferation of datasets with incompatible annotation schemas hinders the development of comprehensive models. While combining…
Redacting Personally Identifiable Information (PII) from unstructured text is critical for ensuring data privacy in regulated domains. While earlier approaches have relied on rule-based systems and domain-specific Named Entity Recognition…
Accurate recognition of specific categories, such as persons' names, dates or other identifiers is critical in many Automatic Speech Recognition (ASR) applications. As these categories represent personal information, ethical use of this…