Current research in cybersecurity is increasingly focused on addressing the vulnerabilities of advanced technologies, particularly large language models and industrial IoT systems. Recent work highlights the critical need for benchmarks like MalURLBench, which evaluates the susceptibility of LLMs to malicious URLs, and frameworks such as MI$^2$DAS, designed to enhance intrusion detection in dynamic IIoT environments. Additionally, the development of automated tools like AEGIS for generating attack paths and CAM-LDS for interpreting system logs signifies a shift towards leveraging automation and machine learning to streamline security processes. The introduction of comprehensive datasets, such as CIC-Trap4Phish, aims to bolster defenses against phishing attacks by providing diverse training materials. Furthermore, the exploration of knowledge graph-guided approaches to enhance the security of retrieval-augmented generation systems reveals a growing recognition of the need for adaptive, intelligent defenses against evolving cyber threats. Collectively, these advancements underscore a proactive approach to mitigating risks in an increasingly complex digital landscape.
Top papers
- MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs(7.0)
- MI$^2$DAS: A Multi-Layer Intrusion Detection Framework with Incremental Learning for Securing Industrial IoT Networks(7.0)
- Decision-Aware Trust Signal Alignment for SOC Alert Triage(6.0)
- AEGIS: White-Box Attack Path Generation using LLMs and Training Effectiveness Evaluation for Large-Scale Cyber Defence Exercises(6.0)
- Resource-Aware Deployment Optimization for Collaborative Intrusion Detection in Layered Networks(6.0)
- CAM-LDS: Cyber Attack Manifestations for Automatic Interpretation of System Logs and Security Alerts(5.0)
- CIC-Trap4Phish: A Unified Multi-Format Dataset for Phishing and Quishing Attachment Detection(5.0)
- Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems(5.0)
- Multi-Targeted Graph Backdoor Attack(4.0)
- Cyber Threat Intelligence for Artificial Intelligence Systems(3.0)
- Evaluating Human and Machine Confidence in Phishing Email Detection: A Comparative Study(3.0)