mlsanityData to 7 Oct 2026

Adversarial News and Lost Profits: Manipulating Headlines in LLM-Driven Algorithmic Trading

arXiv 2601.13082 ↗First posted 19 Jan 2026cs.CR cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) are increasingly adopted in the financial domain. Their exceptional capabilities to analyse textual data make them well-suited for inferring the sentiment of finance-related news. Such feedback can be leveraged by algorithmic trading systems (ATS) to guide buy/sell decisions. However, this practice bears the risk that a threat actor may craft "adversarial news" intended to mislead an LLM. In particular, the news headline may include "malicious" content that remains invisible to human readers but which is still ingested by the LLM. Although prior work has studied textual adversarial examples, their system-wide impact on LLM-supported ATS has not yet been quantified in terms of monetary risk. To address this threat, we consider an adversary with no direct access to an ATS but able to alter stock-related news headlines on a single day. We evaluate two human-imperceptible manipulations in a financial context: Unicode homoglyph substitutions that misroute models during stock-name recognition, and hidden-text clauses that alter the sentiment of the news headline. We implement a realistic ATS in Backtrader that fuses an LSTM-based price forecast with LLM-derived sentiment (FinBERT, FinGPT, FinLLaMA, and six general-purpose LLMs), and quantify monetary impact using portfolio metrics. Experiments on real-world data show that manipulating a one-day attack over 14 months can reliably mislead LLMs and reduce annual returns by up to 17.7 percentage points. To assess real-world feasibility, we analyze popular scraping libraries and trading platforms and survey 27 FinTech practitioners, confirming our hypotheses. We notified trading platform owners of this security issue.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 33 of its 105 references that are in the map. First posted on arXiv 19 Jan 2026.

Builds on

33 of 105 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  5. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
  6. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  7. 2023BloombergGPT: A Large Language Model for Financecited by 923
  8. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  9. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  10. 2023FinGPT: Open-Source Financial Large Language Modelscited by 244
  11. 2024FinBen: A Holistic Financial Benchmark for Large Language Modelscited by 140
  12. 2018TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Timecited by 108
21 more
  1. 2020Sponge Examples: Energy-Latency Attacks on Neural Networkscited by 108
  2. 2020Dos and Don'ts of Machine Learning in Computer Securitycited by 98
  3. 2021Bad Characters: Imperceptible NLP Attackscited by 69
  4. 2020Functionality-preserving Black-box Optimization of Adversarial Windows Malwarecited by 58
  5. 2022"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practicecited by 55
  6. 2020Adversarial Examples in Deep Learning for Multivariate Time Series Regressioncited by 26
  7. 2025Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systemscited by 24
  8. 2024SoK: Dataset Copyright Auditing in Machine Learning Systemscited by 14
  9. 2020Adversarial Attacks on Probabilistic Autoregressive Forecasting Modelscited by 13
  10. 2021Fall of Giants: How popular text-based MLaaS fall against a simple evasion attackcited by 12
  11. 2020Adversarial Attacks on Machine Learning Systems for High-Frequency Tradingcited by 11
  12. 2023BadVFL: Backdoor Attacks in Vertical Federated Learningcited by 9
  13. 2024From ML to LLM: Evaluating the Robustness of Phishing Webpage Detection Models against Adversarial Attackscited by 6
  14. 2022Wild Networks: Exposure of 5G Network Infrastructures to Adversarial Examplescited by 5
  15. 2023When Vision Fails: Text Attacks Against ViT and OCRcited by 5
  16. 2024SoK: On the Offensive Potential of AIcited by 5
  17. 2025FinDPO: Financial Sentiment Analysis for Algorithmic Trading through Preference Optimization of LLMscited by 4
  18. 2025Special-Character Adversarial Attacks on Open-Source Language Modelcited by 4
  19. 2020Taking Over the Stock Market: Adversarial Perturbations Against Algorithmic Traderscited by 3
  20. 2023Automated Market Making and Arbitrage Profits in the Presence of Feescited by 3
  21. 2025The Ephemeral Threat: Assessing the Security of Algorithmic Trading Systems powered by Deep Learningcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Sell Me This Stock: Unsafe Recommendation Drift in LLM Agentscited by 2
  2. 2026Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systemscited by 0
  3. 2026Large Language Model-Driven Small-Capitalization Trading: Integrating Financial News Sentiment, Macroeconomic Indicators, and Technical Signalscited by 0
  4. 2026Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systemscited by 0