Tweezers: A Framework for Security Event Detection via Event Attribution-centric Tweet Embedding
Jian Cui
Network and Distributed System Security (NDSS) Symposium 2025 · Day 3 · Github + OSN Security
This talk introduces **Tweezers**, a novel framework designed to enhance the detection of security events from social media platforms, specifically Twitter. Presented by Jian Cui, a PhD student at Indiana University, in collaboration with Professor Shojun Leo and colleagues from Kais and S2W, Tweezers addresses critical shortcomings in existing methods for extracting actionable threat intelligence from the vast and often noisy landscape of social media. The core innovation lies in its **event attribution-centric tweet embedding** approach, which moves beyond traditional text-based embeddings to leverage the unique security attributes that define and distinguish cyber events.
AI review
Tweezers is competent academic security research with a real problem statement — text embedding models conflating lexically similar but semantically distinct security events is a genuine pain point in automated TI collection. The GATv2 + contrastive loss approach on a STIX-attribute-derived graph is technically coherent, but the evaluation dataset (167 events, 254 tweets) is so small it's hard to take the 'doubled precision and coverage' headline seriously at scale. Solid NDSS paper; reasonable conference slot; won't be what people are talking about at the bar.