paper
Adversarial Creation and Detection of AI-Generated Social Bot Content
paperactiveprovisional
adversarial-creation-and-detection-of-ai-generated-social-bot-content-7db25fde·1 events·first seen 9d agoAliases: Adversarial Creation and Detection of AI-Generated Social Bot Content
More like this (12)
Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision ApplicationsAgentic AI SystemsSafety by Design for Generative AI: Preventing Child Sexual AbuseAdversarial Attacks on Neural Network PoliciesProducerAIAI Safety via DebateThe Malicious Use of Artificial IntelligenceAI vs. AIOpenAI Dota 2 BotshareAI-labthird-party AI evaluationsagentic AI
Recent events (1)
Adversarial methodology improves detection of AI-generated social bot content
Researchers introduce an adversarial framework that simulates malicious actors impersonating real social media users to generate training data for AI-content detection. The approach produces a multilingual, cross-platform dataset of paired human and AI-generated messages. Models trained on this adversarial data significantly outperform existing content-based bot detection systems on out-of-distribution real-world data.