Elie's Cybersecurity Blog
488 FOLLOWERS
Elie Bursztein leads Google's anti-abuse research efforts, sharing his insights on topics relevant to the world of InfoSec on his personal blog.
Elie's Cybersecurity Blog
2w ago
RETSim (Resilient and Efficient Text Similarity) is a lightweight, multilingual robust metric embeddings suitable for near-duplicate text retrieval, clustering, and dataset deduplication tasks ..read more
Elie's Cybersecurity Blog
3w ago
This talk discuss through concrete examples how to use the Google Security AI Framework (SAIF) to protect AI systems and workflows ..read more
Elie's Cybersecurity Blog
3w ago
This talk discuss in concrete terms how large models are currently reshaping cybersecurity from both an offensive and defensive standpoint ..read more
Elie's Cybersecurity Blog
3M ago
This research study presented at NeurIPS 2024 introduces RETVec, a robust and multilingual text vectorizer that provides efficiency and resilience against typos and adversarial attacks for neural-based text processing ..read more
Elie's Cybersecurity Blog
3M ago
We introduce a hybrid digital signature scheme based on two building blocks: a classically-secure scheme, ECDSA, and a post-quantum secure one, Dilithium. Our hybrid scheme maintains the guarantees of each underlying building block even if the other one is broken, thus being resistant to classical and quantum attacks ..read more
Elie's Cybersecurity Blog
3M ago
Exploring the societal impact of the GenAI workforce entering the market ..read more
Elie's Cybersecurity Blog
3M ago
This talk provides an overview of how Google uses AI to strengthen Gmail's document defenses and withstand attacks that evade traditional AVs ..read more
Elie's Cybersecurity Blog
3M ago
This research study presented at CHI investigates the widespread online harassment faced by content creators, and highlights the need for better support and protection on social media platforms ..read more
Elie's Cybersecurity Blog
3M ago
This large-scale study demonstrates, by surveying 17280 participants, that existing toxicity classifiers fail to generalize to the diverse concerns of Internet users ..read more
Elie's Cybersecurity Blog
3M ago
We propose a comprehensive online hate and harassment taxonomy derived from analyzing over 150 interdisciplinary research papers that cover disparate threats ranging from intimate partner violence to coordinated mobs ..read more