Related papers: ClawTrap: A MITM-Based Red-Teaming Framework for R…

We address the challenge of generating diverse attack prompts for large language models (LLMs) that elicit harmful behaviors (e.g., insults, sexual content) and are used for safety fine-tuning. Rather than relying on manual prompt…

To address the increasing complexity and frequency of cybersecurity incidents emphasized by the recent cybersecurity threat reports with over 10 billion instances, cyber threat intelligence (CTI) plays a critical role in the modern…

Jailbreak attacks in large language models (LLMs) entail inducing the models to generate content that breaches ethical and legal norm through the use of malicious prompts, posing a substantial threat to LLM security. Current strategies for…

Customized Large Language Model (LLM) agents face a critical security threat from black-box instruction backdoors, where malicious behaviors are covertly injected through hidden system instructions. Although existing prompt-based defenses…

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…

Recently, people have suffered from LLM hallucination and have become increasingly aware of the reliability gap of LLMs in open and knowledge-intensive tasks. As a result, they have increasingly turned to search-augmented LLMs to mitigate…

Web applications increasingly face evasive and polymorphic attack payloads, yet traditional web application firewalls (WAFs) based on static rule sets such as the OWASP Core Rule Set (CRS) often miss obfuscated or zero-day patterns without…

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for…

Large language models (LLMs) remain vulnerable to a slew of adversarial attacks and jailbreaking methods. One common approach employed by white-hat attackers, or red-teamers, is to process model inputs and outputs using string-level…

The landscape of cyber threats grows more complex by the day. Advanced Persistent Threats carry out attack campaigns - e.g. operations Dream Job, Wocao, and WannaCry - against which cybersecurity practitioners must defend. To prioritise…

Cyber threat intelligence (CTI) is central to modern cybersecurity, providing critical insights for detecting and mitigating evolving threats. With the natural language understanding and reasoning capabilities of large language models…

Recently, red teaming, with roots in security, has become a key evaluative approach to ensure the safety and reliability of Generative Artificial Intelligence. However, most existing work emphasizes technical benchmarks and attack success…

As AI agents increasingly operate in complex environments, ensuring reliable, context-aware privacy is critical for regulatory compliance. Traditional access controls are insufficient because privacy risks often arise after access is…

Public information contains valuable Cyber Threat Intelligence (CTI) that is used to prevent future attacks. While standards exist for sharing this information, much appears in non-standardized news articles or blogs. Monitoring online…

The World Action Model (WAM) can jointly predict future world states and actions, exhibiting stronger physical manipulation capabilities compared with traditional models. Such powerful physical interaction ability is a double-edged sword:…

Over the last years, threat intelligence sharing has steadily grown, leading cybersecurity professionals to access increasingly larger amounts of heterogeneous data. Among those, cyber attacks' Tactics, Techniques and Procedures (TTPs) have…

Tool-augmented LLM agents introduce security risks that extend beyond user-input filtering, including indirect prompt injection through fetched content, unsafe tool execution, credential leakage, and tampering with local control files. We…

With the increasing growth of cyber-attack incidences, it is important to develop innovative and effective techniques to assess and defend networked systems against cyber attacks. One of the well-known techniques for this is performing…

Despite the growing capabilities of autonomous agents powered by large language models (LLMs), their adoption in high-stakes domains remains limited. A key barrier is security: the inherently nondeterministic behavior of LLM agents defies…

Multimodal Large Language Models (MLLMs) achieve strong reasoning and perception capabilities but are increasingly vulnerable to jailbreak attacks. While existing work focuses on explicit attacks, where malicious content resides in a single…