相关论文: Evaluating the Exploitability of Implicit Interact…

Concurrent Kleene Algebra (CKA) is a recently proposed algebraic structure by Hoare and collaborators that unifies the laws of concurrent programming. The unifying power of CKA rests largely on the so-called exchange law that describes how…

The nature of information security has been, and probably will continue to be, marked by the asymmetric competition of attackers and defenders over the control of an uncertain environment. The reduction of this degree of uncertainty via an…

Backdoor attacks pose a serious threat to deep learning models by allowing adversaries to implant hidden behaviors that remain dormant on clean inputs but are maliciously triggered at inference. Existing backdoor attack methods typically…

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial…

Increasing reliance on Information and Communication Technology~(ICT) exposes the power grid to cyber-attacks. In particular, Coordinated Cyber-Attacks (CCAs) are considered highly threatening and difficult to defend against, because they…

As machine learning models become increasingly deployed across the edge of internet of things environments, a partitioned deep learning paradigm in which models are split across multiple computational nodes introduces a new dimension of…

Opacity and attack detectability are important properties for any system as they allow the states to remain private and malicious attacks to be detected, respectively. In this paper, we show that a fundamental trade-off exists between these…

Large language models (LLMs) have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to limited interaction, weak execution grounding, and a lack of…

Cyber-physical control systems, such as industrial control systems (ICS), are increasingly targeted by cyberattacks. Such attacks can potentially cause tremendous damage, affect critical infrastructure or even jeopardize human life when the…

As one of the largest and most complex systems on earth, power grid (PG) operation and control have stepped forward as a compound analysis on both physical and cyber layers which makes it vulnerable to assaults from economic and security…

Interactive behavior modeling of multiple agents is an essential challenge in simulation, especially in scenarios when agents need to avoid collisions and cooperate at the same time. Humans can interact with others without explicit…

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…

This paper introduces a multi-round interaction problem with privacy constraints between two agents that observe correlated data. The agents alternately share data with one another for a total of K rounds such that each agent initiates…

A Large Language Model (LLM) powered GUI agent is a specialized autonomous system that performs tasks on the user's behalf according to high-level instructions. It does so by perceiving and interpreting the graphical user interfaces (GUIs)…

This work focuses on the use of deep learning for vulnerability analysis of cyber-physical systems (CPS). Specifically, we consider a control architecture widely used in CPS (e.g., robotics), where the low-level control is based on e.g.,…

Deep learning systems, critical in domains like autonomous vehicles, are vulnerable to adversarial examples (crafted inputs designed to mislead classifiers). This study investigates black-box adversarial attacks in computer vision. This is…

The theory of controlled quantum open systems describes quantum systems interacting with quantum environments and influenced by external forces varying according to given algorithms. It is aimed, for instance, to model quantum devices which…

In this paper, we model and analyze how a network of interacting LLMs performs collaborative question-answering (CQA) in order to estimate a ground truth given a distributed set of documents. This problem is interesting because LLMs often…

There has been a large number of studies in interpretable and explainable ML for cybersecurity, in particular, for intrusion detection. Many of these studies have significant amount of overlapping and repeated evaluations and analysis. At…

Autonomous Large Language Model (LLM) agents exhibit significant vulnerability to Indirect Prompt Injection (IPI) attacks. These attacks hijack agent behavior by polluting external information sources, exploiting fundamental trade-offs…