相关论文: Chasing the Shadows: TTPs in Action to Attribute A…

Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available,…

Cyber threat hunting is the practice of proactively searching for latent threats in a network. Engaging in threat hunting can be difficult due to the volume of network traffic, variety of adversary techniques, and constantly evolving…

The robustness and generalization ability of Presentation Attack Detection (PAD) methods is critical to ensure the security of Face Recognition Systems (FRSs). However, in a real scenario, Presentation Attacks (PAs) are various and it is…

AI agents are increasingly deployed to act autonomously in the world, yet there is still no reliable way to trace a harmful agent back to the account that deployed it. This creates the same accountability gap across both ends of the intent…

With the great advancements in large language models (LLMs), adversarial attacks against LLMs have recently attracted increasing attention. We found that pre-existing adversarial attack methodologies exhibit limited transferability and are…

As our cities and communities become smarter, the systems that keep us safe, such as traffic control centers, emergency response networks, and public transportation, also become more complex. With this complexity comes a greater risk of…

The MITRE ATT&CK Framework provides a rich and actionable repository of adversarial tactics, techniques, and procedures (TTP). However, this information would be highly useful for attack diagnosis (i.e., forensics) and mitigation (i.e.,…

The self-attention mechanism has been adopted in various popular message passing neural networks (MPNNs), enabling the model to adaptively control the amount of information that flows along the edges of the underlying graph. Such…

Advanced Persistent Threats or APTs are big challenges to the security of government organizations or industry systems. These threats may result in stealth attacks, but if the attack is confronted before the attacker end goal has been…

When multi-agent systems (MAS) fail, identifying where the decisive error occurred is the first step for automated recovery to an earlier state. Error attribution remains a fundamental challenge due to the long interaction traces that large…

Anomaly detection is critical to ensure the security of cyber-physical systems (CPS). However, due to the increasing complexity of attacks and CPS themselves, anomaly detection in CPS is becoming more and more challenging. In our previous…

Long-context large language models (LLMs), such as Gemini-2.5-Pro and Claude-Sonnet-4, are increasingly used to empower advanced AI systems, including retrieval-augmented generation (RAG) pipelines and autonomous agents. In these systems,…

Data provenance (the process of determining the origin and derivation of data outputs) has applications across multiple domains including explaining database query results and auditing scientific workflows. Despite decades of research,…

Recent research has revealed that the security of deep neural networks that directly process 3D point clouds to classify objects can be threatened by adversarial samples. Although existing adversarial attack methods achieve high success…

LLM agents are highly vulnerable to Indirect Prompt Injection (IPI), where adversaries embed malicious directives in untrusted tool outputs to hijack execution. Most existing defenses treat IPI as an input-level semantic discrimination…

Attack paths are the potential chain of malicious activities an attacker performs to compromise network assets and acquire privileges through exploiting network vulnerabilities. Attack path analysis helps organizations to identify…

Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection…

Cyber attacks are often identified using system and network logs. There have been significant prior works that utilize provenance graphs and ML techniques to detect attacks, specifically advanced persistent threats, which are very difficult…

Studying adversarial attacks on artificial intelligence (AI) systems helps discover model shortcomings, enabling the construction of a more robust system. Most existing adversarial attack methods only concentrate on single-task single-model…

Multi-Task Learning (MTL) is a foundational machine learning problem that has seen extensive development over the past decade. Recently, various optimization-based MTL approaches have been proposed to learn multiple tasks simultaneously by…