173 citations
- Cisco Systems (United States)US4 papers
- FC BarcelonaES3 papers
- Rutgers, The State University of New JerseyUS3 papers
- Universitat Politècnica de CatalunyaES3 papers
- University of Southern CaliforniaUS3 papers
- Washington University in St. LouisUS3 papers
- Adobe Systems (United States)US2 papers
- Brigham and Women's HospitalUS2 papers
- Cisco Systems (China)CN2 papers
- Cornell UniversityUS2 papers
- Google (United States)US2 papers
- Harvard University PressUS2 papers
20 papers
Towards Traffic Modelling of Multi-Agent Systems: The Role of Coordination Topology
Davide Lamagna, Albert Cabellos, Alberto Rodriguez-Natal +2
Multi-agent LLM systems are an emerging networked workload whose rapid deployment raises questions about the traffic patterns they generate. Compared to conventional applications,…
Cornserve: A Distributed Serving System for Any-to-Any Multimodal Models
Jae-Won Chung, Jeff J. Ma, Jisang Ahn +4
Any-to-Any models are an emerging class of multimodal models that accept combinations of multimodal data (e.g., text, image, video, audio) as input and generate them as output. Ser…
Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation
Zhisheng Qi, Utkarsh Sahu, Li Ma +9
Retrieval-Augmented Generation (RAG) has become a cornerstone of knowledge-intensive applications, including enterprise chatbots, healthcare assistants, and agentic memory manageme…
SecureBERT 2.0: Advanced Language Model for Cybersecurity Intelligence
Ehsan Aghaei, Sarthak Jain, Prashanth Arun +1
Effective analysis of cybersecurity and threat intelligence data demands language models that can interpret specialized terminology, complex document structures, and the interdepen…
LMN: A Tool for Generating Machine Enforceable Policies from Natural Language Access Control Rules using LLMs
Pratik Sonune, Ritwik Rai, Shamik Sural +2
Organizations often lay down rules or guidelines called Natural Language Access Control Policies (NLACPs) for specifying who gets access to which information and when. However, the…
Network-informed Prompt Engineering against Organized Astroturf Campaigns under Extreme Class Imbalance
Nikos Kanakaris, Heng Ping, Xiongye Xiao +4
Detecting organized political campaigns is of paramount importance in fighting against disinformation on social media. Existing approaches for the identification of such organized…