相关论文: HARMer: Cyber-attacks Automation and Evaluation

Human-in-the-loop reinforcement learning integrates human expertise to accelerate agent learning and provide critical guidance and feedback in complex fields. However, many existing approaches focus on single-agent tasks and require…

Stealth attacks pose potential risks to cyber-physical systems because they are difficult to detect. Assessing the risk of systems under stealth attacks remains an open challenge, especially in nonlinear systems. To comprehensively quantify…

As Industry 4.0 and digitalization continue to advance, the reliance on information technology increases, making the world more vulnerable to cyber-attacks, especially cyber-physical attacks that can manipulate physical systems and…

Modern adversarial campaigns unfold as sequences of behavioural phases - Reconnaissance, Lateral Movement, Intrusion, and Exfiltration - each often indistinguishable from legitimate traffic when viewed in isolation. Existing intrusion…

This paper explores the evolving dynamics of cybersecurity in the age of advanced AI, from the perspective of the introduced Human Layer Kill Chain framework. As traditional attack models like Lockheed Martin's Cyber Kill Chain become…

Automated red-teaming has become a crucial approach for uncovering vulnerabilities in large language models (LLMs). However, most existing methods focus on isolated safety flaws, limiting their ability to adapt to dynamic defenses and…

Graph-based frameworks are often used in network hardening to help a cyber defender understand how a network can be attacked and how the best defenses can be deployed. However, incorporating network connectivity parameters in the attack…

Penetration testing and vulnerability assessment are essential industry practices for safeguarding computer systems. As cyber threats grow in scale and complexity, the demand for pentesting has surged, surpassing the capacity of human…

The transition to smart grids has increased the vulnerability of electrical power systems to advanced cyber threats. To safeguard these systems, comprehensive security measures-including preventive, detective, and reactive strategies-are…

Multi-agent reinforcement learning (MARL) is a powerful paradigm for solving cooperative and competitive decision-making problems. While many MARL benchmarks have been proposed, few combine continuous state and action spaces with…

Existing automated attack suites operate as static ensembles with fixed sequences, lacking strategic adaptation and semantic awareness. This paper introduces the Agentic Reasoning for Methods Orchestration and Reparameterization (ARMOR)…

Security operators use red teams to simulate real attackers and proactively find defense gaps. In realistic enterprise settings, this involves executing multi-host network attacks spanning many "stepping stone" hosts. Unfortunately, red…

As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect and mitigate risks. Large Language Models (LLMs) offer promising capabilities for enhancing threat…

Cyber attacks threaten economic interests, critical infrastructure, and public health and safety. To counter this, entities adopt cyber threat hunting, a proactive approach that involves formulating hypotheses and searching for attack…

Automated red teaming can discover rare model failures and generate challenging examples that can be used for training or evaluation. However, a core challenge in automated red teaming is ensuring that the attacks are both diverse and…

Task-oriented LLM-based agents are increasingly used in domains with strict policies, such as refund eligibility or cancellation rules. The challenge lies in ensuring that the agent consistently adheres to these rules and policies,…

With the ever-changing landscape of cyber threats, identifying their origin has become paramount, surpassing the simple task of attack classification. Cyber threat attribution gives security analysts the insights they need to device…

Offensive security-tests are a common way to pro-actively discover potential vulnerabilities. They are performed by specialists, often called penetration-testers or white-hat hackers. The chronic lack of available white-hat hackers prevents…

We implemented and evaluated an automated cyber defense agent. The agent takes security alerts as input and uses reinforcement learning to learn a policy for executing predefined defensive measures. The defender policies were trained in an…

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…