# Breaking and Defending LLM-Powered Social Media Bot Detection Systems

arXiv: https://arxiv.org/abs/2608.15893 · HTML: https://mlsanity.com/paper/2608.15893/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 16 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [Formalizing and Benchmarking Prompt Injection Attacks and Defenses](https://mlsanity.com/paper/2310.12815/) (2023)
- [Poisoning Language Models During Instruction Tuning](https://mlsanity.com/paper/2305.00944/) (2023)
- [Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation](https://mlsanity.com/paper/2311.03348/) (2023)
- [Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey](https://mlsanity.com/paper/2402.09283/) (2024)
- [Evil Geniuses: Delving into the Safety of LLM-based Agents](https://mlsanity.com/paper/2311.11855/) (2023)
- [TwiBot-20: A Comprehensive Twitter Bot Detection Benchmark](https://mlsanity.com/paper/2106.13088/) (2021)
- [The paradigm-shift of social spambots: Evidence, theories, and tools for the arms race](https://mlsanity.com/paper/1701.03017/) (2017)
- [TwiBot-22: Towards Graph-Based Twitter Bot Detection](https://mlsanity.com/paper/2206.04564/) (2022)
- [Heterogeneity-aware Twitter Bot Detection with Relational Graph Transformers](https://mlsanity.com/paper/2109.02927/) (2021)
- [Botometer 101: Social bot practicum for computational social scientists](https://mlsanity.com/paper/2201.01608/) (2022)
- [What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection](https://mlsanity.com/paper/2402.00371/) (2024)
- [LMBot: Distilling Graph Knowledge into Language Model for Graph-less Deployment in Twitter Bot Detection](https://mlsanity.com/paper/2306.17408/) (2023)
- [BotTriNet: A Unified and Efficient Embedding for Social Bots Detection via Metric Learning](https://mlsanity.com/paper/2304.03144/) (2023)

## Abstract (arXiv)

The rise of social media bots poses a persistent threat, enabling misinformation, opinion manipulation, and the erosion of trust in online platforms. To combat this, machine learning systems have been developed to detect and limit bot activity, but attackers continuously adapt through techniques such as adversarial learning and behavior imitation, fueling an ongoing arms race between bots and detection tools. Recent advances in large language models (LLMs) have significantly improved bot detection by enabling deeper semantic and contextual analysis of accounts and their content. However, this shift also introduces new attack surfaces, allowing adversaries to craft exploits that directly target the reasoning and generation mechanisms of LLM-based classifiers. Industry tools such as Anthropic's Claude Code Security similarly leverage LLMs for security-critical decisions, further motivating a careful study of their attack surfaces. In this work, we investigate both the offensive and defensive aspects of LLM-powered, threat-specific cybersecurity applications. While centered on the challenge of social media bot detection, our methodology and insights generalize to a broad class of LLM-powered cybersecurity systems, including phishing detection, email classification, and fraud analysis. We introduce two novel adversarial attack strategies that systematically exploit the semantic and contextual weaknesses of LLM-based classifiers, degrading their detection accuracy by up to 48%. To counter these threats, we propose a robust multi-LLM defense architecture designed to preserve detection reliability under adaptive adversarial conditions. Our solution, LSABRE (LLM-powered Social Adversarial Bot Recognition Ensemble), is a multi-LLM framework that substantially improves robustness across a range of attacks, maintaining 86% detection accuracy even under strong, adaptive adversarial pressure.