Spam Fighting @Scale 2015
as the organisers put it
Engineering better abuse detection: Spam Fighting@Scale is an invitation-only technical conference for engineers working on large-scale management and analytics solutions for platform abuse. Building applications and services that scale presents a complex set of engineering challenges. Join engineers from Facebook, LinkedIn, Snapchat, and WhatsApp for discussions on fighting malicious apps, measuring spam, leveraging user-generated input, detecting fake […]
who it's for
anti-abuse engineers, platform engineers, security engineers, machine learning engineers, data scientists, fraud analysts, site reliability engineers
topics
naive Bayes n-gram model; random forest cluster model; locality sensitive hashing; DGIM time-window counters; sliding HyperLogLog uniques; rule engine with DSL; graph database threat sharing; Yara Suricata Bro Snort signatures; phone verification reputation classifier; photo clustering pipeline; binomial anomaly detection; Kafka Storm Spark pipeline
| title | author | length |
|---|---|---|
| Finding Spam in Short Text Fields | Sayan Dasgupta, Ted Hwa | 21m |
LinkedIn builds a language-agnostic naive Bayes n-gram model that scores names using character n-grams, handling unseen n-grams by aggregation or recursive… | ||
| Closing Remarks | Kristie Chow | 03m |
Ninety percent of the morning audience still stays, and the meeting ends with concrete takeaways: spam fighting is hard but communal, product fixes sometimes… | ||
| Platform Integrity: Lessons Learned in Protecting the Facebook Platform | Jonathan Gross | 31m |
Facebook reports hundreds or thousands of malicious apps every day and defends by logging every app event, aggregating time-window counters in a real-time… | ||
| The Role of ThreatExchange | Mark Hammell | 27m |
Facebook builds ThreatExchange, an API-based platform that shares indicators (IPs, domains, URLs), malware samples and Yara Suricata Bro Snort signatures with… | ||
| Spam-fighting Infrastructure | Marcin Pawlowski | 36m |
Describes an executable rule engine built on Haxl rule engine that enforces pure-function rules with lazy, overlapping data fetches to keep synchronous path… | ||
| Spam-fighting Strategy | Jieqi Yu, Isaac Fullinwider | 34m |
Facebook describes an implemented pipeline that combines an online counter system and an offline clustering system to catch spam by aggregating weak signals… | ||
| A brief history of fighting spam at Pinterest | Chris Walters | 35m |
History of Pinterest spam defense traces a move from manual "shift-click" removals to a centralized spam service, an asynchronous pipeline called stingray… | ||
| Welcome to Spam Fighting @Scale | Gregg Stefancik | 12m |
Facebook runs spam defense at 1.4 billion monthly active users and treats anti‑abuse as a service that can cut onboarding from a year to months for… | ||
| nothing matches | ||