Image credit: Jason LucasAbstract
Artificial intelligence has progressed rapidly since its origins in the 1950s, with natural language processing emerging as a critical subfield focused on enabling human-language understanding in machines. In this invited talk, we will discuss a highly influential paper from the 2023 Empirical Methods in Natural Language Processing conference proceedings – “Fighting Fire with Fire." This work introduces new techniques for adversarial attacks against AI systems, revealing vulnerabilities by inducing model misclassifications. However, it also demonstrates the dual capacity to combat maliciously generated text. Discussing both aspects shows how the field is advancing while addressing crucial issues around safety and security. Overall, the 2023 conference features over 900 papers spanning innovations in Large Langauge Models, translation, and more – with a highly-selective 23% acceptance rate. This represents the remarkable progress in AI, while also highlighting important frontiers related to robustness, quality assurance, and positive real-world impact as the technology grows more advanced. We look forward to an engaging overview of the latest advancements and future directions for AI.
Slides can be added in a few ways:
- Create slides using Hugo Blox Builder’s Slides feature and link using
slidesparameter in the front matter of the talk file - Upload an existing slide deck to
static/and link usingurl_slidesparameter in the front matter of the talk file - Embed your slides (e.g. Google Slides) or presentation video on this page using shortcodes.
Further event details, including page elements such as image galleries, can be added to the body of this page.
Jason Lucas
Ph.D. Student in Informatics
My research interests include low-resource multilingual NLP, linguistics, adversarial machine learning and mis/disinformation generation/detection. My Ph.D. thesis is in the area of applying artificial intelligence for cybersecurity and social good, with a focus on low-resource multilingual natural language processing. More specifically, I develop NLP techniques to promote cybersecurity, combat mis/disinformation, and enable AI accessibility for non-English languages and underserved populations. This involves creating novel models and techniques for tasks like multilingual and crosslingual text classification, machine translation, text generation, and adversarial attacks in limited training data settings. My goal is to democratize state-of-the-art AI capabilities by extending them beyond high-resource languages like English into the long tail of lower-resourced languages worldwide. By innovating robust learning approaches from scarce linguistic data, this research aims to open promising directions where AI can have dual benefits strengthening security, integrity and social welfare across diverse global locales.