TRACE-Bot: Detecting Emerging LLM-Driven Social Bots via Implicit Semantic Representations and AIGC-Enhanced Behavioral Patterns

Dimensions overall score 7.0

GitHub Code Pulse

No public code linked for this paper yet.

• TRACE-Bot achieves state-of-the-art performance on two public LLM-driven social bot datasets with accuracies of 98.46% and 97.50%.result 95%
• Existing methods for detecting LLM-driven social bots suffer from limited detection accuracy due to overreliance on single-modality signals.limitation 85%
• TRACE-Bot uses a unified dual-channel framework that jointly models implicit semantic representations and AIGC-enhanced behavioral patterns.method 90%
• TRACE-Bot constructs fine-grained representations from heterogeneous sources including personal information data, interaction behavior data and tweet data.method 85%
• TRACE-Bot demonstrates strong robustness against advanced bot strategies.result 80%
• Existing methods fail to adequately model the interplay between linguistic patterns and behavioral dynamics.limitation 85%
• TRACE-Bot's dual-channel architecture captures linguistic representations via a pretrained language model and behavioral irregularities via multidimensional activity features.technical 85%
• LLM-driven social bots pose a growing threat to online discourse by generating human-like content that evades conventional detection.market 80%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card