Adversarial ML

BLUFF: Benchmarking in Low-resoUrce Languages for detecting Falsehoods and Fake news featured image
Multilingual NLP

BLUFF: Benchmarking in Low-resoUrce Languages for detecting Falsehoods and Fake news

BLUFF is the largest multilingual fake news detection benchmark, spanning 79 languages with 202K+ samples. It introduces AXL-CoI for adversarial generation and mPURIFY for quality …

avatar
Jason Lucas
•
Read more
AI Robustness & Adversarial Safety featured image
Adversarial ML

AI Robustness & Adversarial Safety

Investigating how dialect diversity, authorship obfuscation, and expert-level text editing expose critical vulnerabilities in content detection systems.

Read more
Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation featured image
Adversarial ML

Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation

This research project is a collaboration with Penn State and MIT Lincoln Lab. Our study demonstrates the dual capacity of LLMs for offensive misuse and defense detection against …

avatar
Jason Lucas
•
Read more