Related papers: A Novel Approach To User Agent String Parsing For …
We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…
Modern news is often comprehensive, weaving together information from diverse domains, including technology, finance, and agriculture. This very comprehensiveness creates a challenge for interpretation, as audiences typically possess…
Large Language Model (LLM) web agents often struggle with long-horizon web navigation and web task completion in new websites, producing inefficient action sequences unless fine-tuned on environment-specific data. We show that…
Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces. Concerning the information aggregation, a common practice is to use a concatenation followed by a…
Context and Motivation Attack-Defense Trees (ADTs) are a graphical notation used to model and assess security requirements. ADTs are widely popular, as they can facilitate communication between different stakeholders involved in system…
Ensuring that critical IoT systems function safely and smoothly depends a lot on finding anomalies quickly. As more complex systems, like smart healthcare, energy grids and industrial automation, appear, it is easier to see the shortcomings…
With the advancement of Large-Language Models (LLMs) and Large Vision-Language Models (LVMs), agents have shown significant capabilities in various tasks, such as data analysis, gaming, or code generation. Recently, there has been a surge…
Web Application Firewalls (WAFs) have been introduced as essential and popular security gates that inspect incoming HTTP traffic to filter out malicious requests and provide defenses against a diverse array of web-based threats. Evading…
Deep neural networks (DNNs) can be easily fooled by adversarial attacks during inference phase when attackers add imperceptible perturbations to original examples, i.e., adversarial examples. Many works focus on adversarial detection and…
Despite the robust security features inherent in the 5G framework, attackers will still discover ways to disrupt 5G unmanned aerial vehicle (UAV) operations and decrease UAV control communication performance in Air-to-Ground (A2G) links.…
Cybersecurity has become one of the earliest adopters of agentic AI, as security operations centers increasingly rely on multi-step reasoning, tool-driven analysis, and rapid decision-making under pressure. While individual large language…
Existing aspect based sentiment analysis (ABSA) approaches leverage various neural network models to extract the aspect sentiments via learning aspect-specific feature representations. However, these approaches heavily rely on manual…
Network densification and millimeter-wave technologies are key enablers to fulfill the capacity and data rate requirements of the fifth generation (5G) of mobile networks. In this context, designing low-complexity policies with local…
The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web…
Analyzing individual emotions during group conversation is crucial in developing intelligent agents capable of natural human-machine interaction. While reliable emotion recognition techniques depend on different modalities (text, audio,…
Large language models (LLMs) have empowered nodes within multi-agent networks with intelligence, showing growing applications in both academia and industry. However, how to prevent these networks from generating malicious information…
Internet of Things (IoT) networks generate diverse and high-volume traffic that reflects both normal activity and potential threats. Deriving meaningful insight from such telemetry requires cross-layer interpretation of behaviors,…
Large language models (LLMs) have moved far beyond their initial form as simple chatbots, now carrying out complex reasoning, planning, writing, coding, and research tasks. These skills overlap significantly with those that human scientists…
Deep neural networks for natural language processing tasks are vulnerable to adversarial input perturbations. In this paper, we present a versatile language for programmatically specifying string transformations -- e.g., insertions,…
During the onset of a disaster event, filtering relevant information from the social web data is challenging due to its sparse availability and practical limitations in labeling datasets of an ongoing crisis. In this paper, we hypothesize…