arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.02147cs.AI
收藏

TRACE-Bot:通过隐式语义表示和AIGC增强的行为模式检测新兴的LLM驱动社交机器人

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

Sichuan University(四川大学);Peking University(北京大学)

Zhongbo Wang, Zhiyu Lin, Zhu Wang, Haizhou Wang

AI总结:

本文提出TRACE-Bot框架,通过联合建模隐式语义表示和AIGC增强的行为模式,有效检测新兴LLM驱动社交机器人,实验表明其在两个公开数据集上达到98.46%和97.50%的准确率。

摘要:

大型语言模型驱动(LLM驱动)的社交机器人对在线讨论构成日益增长的威胁,因其生成的人类样内容能够逃避传统检测。现有方法由于过度依赖单一模态信号、对人工智能生成内容(AIGC)特定生成模式的敏感性不足以及未能充分建模语言模式与行为动态的相互作用而存在检测精度有限的问题。为了解决这些限制,我们提出了TRACE-Bot,一个统一的双通道框架,联合建模隐式语义表示和AIGC增强的行为模式。TRACE-Bot从异构来源构建细粒度表示,包括个人信息数据、交互行为数据和推文数据。双通道架构通过预训练语言模型捕获语言表示,并通过多维活动特征增强的信号从最先进的(SOTA)AIGC检测器中捕获行为异常。融合的表示随后通过轻量级预测头进行分类。在两个公开的LLM驱动社交机器人数据集上的实验表明,该方法取得了SOTA性能,分别达到98.46%和97.50%的准确率。结果进一步表明了对高级机器人策略的强鲁棒性,突显了联合利用隐式语义表示和AIGC增强的行为模式在新兴LLM驱动社交机器人检测中的有效性。

英文摘要:

Large Language Model-driven (LLM-driven) social bots pose a growing threat to online discourse by generating human-like content that evades conventional detection. Existing methods suffer from limited detection accuracy due to overreliance on single-modality signals, insufficient sensitivity to the specific generative patterns of Artificial Intelligence-Generated Content (AIGC), and a failure to adequately model the interplay between linguistic patterns and behavioral dynamics. To address these limitations, we propose TRACE-Bot, a unified dual-channel framework that jointly models implicit semantic representations and AIGC-enhanced behavioral patterns. TRACE-Bot constructs fine-grained representations from heterogeneous sources, including personal information data, interaction behavior data and tweet data. A dual-channel architecture captures linguistic representations via a pretrained language model and behavioral irregularities via multidimensional activity features augmented with signals from state-of-the-art (SOTA) AIGC detectors. The fused representations are then classified through a lightweight prediction head. Experiments on two public LLM-driven social bot datasets demonstrate SOTA performance, achieving accuracies of 98.46% and 97.50%, respectively. The results further indicate strong robustness against advanced bot strategies, highlighting the effectiveness of jointly leveraging implicit semantic representations and AIGC-enhanced behavioral patterns for emerging LLM-driven social bot detection.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑