The 2024 Conference on Empirical Methods in Natural Language Processing
November 12-16, 2024 in Miami, Florida
The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP) is a premier event showcasing the latest advancements in NLP research and applications. It brings together experts from academia and industry to discuss cutting-edge methodologies, share groundbreaking findings, and explore future directions in the field of natural language processing.
Kitware is excited to be attending EMNLP and is proud to announce that we had a paper accepted at this prestigious event. As a leader in developing innovative solutions across various domains, we are thrilled to engage with the vibrant NLP community and explore the latest advancements in the field. Our team is actively working on groundbreaking projects that leverage NLP to solve complex challenges, including combating disinformation, and we are looking forward to sharing our work and learning from the brilliant researchers and experts attending EMNLP.
We are also expanding our team and currently hiring NLP researchers and experts who are passionate about pushing the boundaries of technology. Read more about our featured open positions below.
Kitware’s Activities and Involvement
Defending Against Social Engineering Attacks in the Age of LLMs
Paper
Authors: Lin Ai, Tharindu Sandaruwan Kumarage, Amrita Bhattacharjee, Zizhou Liu, Zheng Hui, Michael S. Davinroy, James Cook, Laura Cassani, Kirill Trapeznikov, Matthias Kirchner (Kitware), Arslan Basharat (Kitware), Anthony Hoogs (Kitware), Joshua Garland, huan liu, Julia Hirschberg
This paper explores the challenges posed by Large Language Models (LLMs) in detecting and preventing digital deception, particularly in chat-based social engineering (CSE) attacks. The authors investigate the dual role of LLMs, both as tools for facilitating CSE threats and as potential defenses. To study this, they develop a dataset called SEConvo, simulating CSE scenarios in academic and recruitment settings. Their findings show that while LLMs can generate convincing CSE content, their ability to detect such threats is limited, resulting in higher defense costs. To address this, they introduce ConvoSentinel, a modular defense system that improves detection at both the message and conversation levels. This system uses a retrieval-augmented module to compare suspicious messages to a database of similar conversations, enhancing the detection of malicious intent. The paper underscores the need for more sophisticated strategies to use LLMs in cybersecurity effectively.
Kitware is hiring!
Join us at Kitware to collaborate on cutting-edge projects, contribute to the advancement of NLP, and help develop state-of-the-art solutions that make a real-world impact. Apply now!
Featured Open Positions
Natural Language Processing Researcher (Hybrid or Remote)
Locations: Remote; Clifton Park, New York; Carrboro, North Carolina; Minneapolis, Minnesota; Arlington, Virginia
We are seeking a talented researcher to develop innovative solutions in Natural Language Processing, Large Language Models, Foundation Models, Machine Learning, and AI. You will create and evaluate algorithms to understand and reason with textual and multi-modal data. We support active participation in leading national and international conferences, and you’ll have the opportunity to seek funding to expand your own research areas. Join us to push the boundaries of NLP and AI research!
Technical Leader of Natural Language Processing (Hybrid or Remote)
Locations: Remote; Clifton Park, New York; Carrboro, North Carolina; Minneapolis, Minnesota; Arlington, Virginia
We are looking for a dynamic leader with technical expertise and project management skills to guide small teams on cutting-edge R&D projects for government and commercial clients. In this role, you will collaborate with renowned academic and industry researchers, develop innovative algorithms to analyze and reason with textual and multi-modal data, and lead proposals for new funding opportunities. You’ll also have the chance to contribute to the research community by participating in leading conferences in NLP, ML, AI, and computer vision. Join us to drive impactful research and innovation in these fields!
Computer Vision at Kitware
Kitware is a leader in leveraging artificial intelligence and machine learning for computer vision. Our technical areas of focus include:
- Generative AI
- Multimodal large language models
- Deep learning
- Dataset collection and annotation
- Interactive Do-It-Yourself AI
- Explainable and ethical AI
- Object detection, classification, and tracking
- Complex activity, event, and threat detection
- Cyber-physical systems
- Disinformation detection
- 3D vision
- Super-resolution and enhancement
- Semantic segmentation
- Computational imaging
Kitware’s commitment to continuous exploration and participation in other research and development areas is unwavering. We are always ready to apply our technologies and tools across all domains, from undersea to space, to meet our customers’ needs.
We recognize the value of leveraging our advanced computer vision and deep learning capabilities to support academia, industry, and the DoD and intelligence communities. We work with various government agencies, such as the Defense Advanced Research Project Agency (DARPA), Air Force Research Laboratory (AFRL), the Office of Naval Research (ONR), Intelligence Advanced Research Projects Activity (IARPA), the National Geospatial Intelligence Agency (NGA), U.S. Army and the U.S. Air Force. We also partner with prestigious academic institutions on government contracts.
Kitware can help you solve your challenging computer vision problems using our software R&D expertise. Contact our team to learn more about how we can partner with you.