相关论文: AIQL: Enabling Efficient Attack Investigation from…

Keeping up with threat intelligence is a must for a security analyst today. There is a volume of information present in `the wild' that affects an organization. We need to develop an artificial intelligence system that scours the…

The increasing interconnection of industrial networks exposes them to an ever-growing risk of cyber attacks. To reveal such attacks early and prevent any damage, industrial intrusion detection searches for anomalies in otherwise predictable…

The advent of large language models is contributing to the emergence of novel approaches that promise to better tackle the challenge of generating structured queries, such as SPARQL queries, from natural language. However, these new…

The scarcity of data and the high complexity of Advanced Persistent Threats (APTs) attacks have created challenges in comprehending their behavior and hindered the exploration of effective detection techniques. To create an effective APT…

The amount of multidimensional data published on the semantic web (SW) is constantly increasing, due to initiatives such as Open Data and Open Government Data, among other ones. Models, languages, and tools, that allow to obtain valuable…

The World Wide Web currently evolves into a Web of Linked Data where content providers publish and link data as they have done with hypertext for the last 20 years. While the declarative query language SPARQL is the de facto for querying…

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…

Advanced Persistent Threat (APT) attack, also known as directed threat attack, refers to the continuous and effective attack activities carried out by an organization on a specific object. They are covert, persistent and targeted, which are…

We present Attentive Reasoning Queries (ARQs), a novel structured reasoning approach that significantly improves instruction-following in Large Language Models through domain-specialized reasoning blueprints. While LLMs demonstrate…

In-context learning (ICL) has become a powerful, data-efficient paradigm for text classification using large language models. However, its robustness against realistic adversarial threats remains largely unexplored. We introduce ICL-Evader,…

Recent research in both academia and industry has validated the effectiveness of provenance graph-based detection for advanced cyber attack detection and investigation. However, analyzing large-scale provenance graphs often results in…

Advanced Persistent Threat (APT) attacks are highly sophisticated and employ a multitude of advanced methods and techniques to target organizations and steal sensitive and confidential information. APT attacks consist of multiple stages and…

Attack knowledge graph construction seeks to convert textual cyber threat intelligence (CTI) reports into structured representations, portraying the evolutionary traces of cyber attacks. Even though previous research has proposed various…

Enterprises are constantly under attack from sophisticated adversaries. These adversaries use a variety of techniques to first gain access to the enterprise, then spread laterally inside its networks, establish persistence, and finally…

Effective Cyber Threat Intelligence (CTI) relies upon accurately structured and semantically enriched information extracted from cybersecurity system logs. However, current methodologies often struggle to identify and interpret malicious…

With advances in large language models (LLMs), researchers are creating new systems that can perform AI-driven analytics over large unstructured datasets. Recent work has explored executing such analytics queries using semantic operators --…

A popular class of defenses against prompt injection attacks on large language models (LLMs) relies on fine-tuning to separate instructions and data, so that the LLM does not follow instructions that might be present with data. We evaluate…

Log analysis is crucial for ensuring the orderly and stable operation of information systems, particularly in the field of Artificial Intelligence for IT Operations (AIOps). Large Language Models (LLMs) have demonstrated significant…

Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of…

This paper introduces AQA-Bench, a novel benchmark to assess the sequential reasoning capabilities of large language models (LLMs) in algorithmic contexts, such as depth-first search (DFS). The key feature of our evaluation benchmark lies…