EUVIMEDEUVIMED entdecken
Crossref

Semantics-Preserving Adversarial Attacks on Event-Driven Stock Prediction Models

Aofan Liu, Haoxuan Li, Hongjian Xing, Yuguo Yin, Zijun Li, Yiyan Qi

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (44) · 37645-37653

DOI: 10.1609/aaai.v40i44.41099 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Aofan Liu und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Adversarial Security of Financial Language Models (ASFLM) is critical as Large Language Models (LLMs) pervade high-stakes financial applications. However, LLMs face two key challenges: their vulnerability to damaging adversarial attacks and the prevalent research gap concerning robust defenses against sophisticated, semantically coherent threats. To address these, we first theoretically analyze the relationship between discrete and continuous adversarial optimization, proving the continuous optimum provides a lower bound for the discrete. This foundation supports our novel two-stage framework, ChameleonAttack. It employs Adaptive Latent-space Optimization (ALO) for potent adversarial token discovery, followed by a Semantic-Translation Module (STM) module to generate fluent, coherent, and natural-sounding adversarial text. This dual approach aims to maximize attack impact while ensuring high linguistic quality and semantic integrity for evasion. Evaluated on state-of-the-art financial LLMs (e.g., FinBERT) and standard benchmarks (e.g., Financial PhraseBank), ChameleonAttack achieves a high Attack Success Rate (ASR) of 93.4%. These results highlight significant practical vulnerabilities and underscore the urgent need for robust defense mechanisms in the financial domain.

Zitieren

APA

Liu, A., Li, H., Xing, H., Yin, Y., Li, Z., & Qi, Y. (2026). Semantics-Preserving Adversarial Attacks on Event-Driven Stock Prediction Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(44), 37645-37653. https://doi.org/10.1609/aaai.v40i44.41099

Vancouver

Liu A, Li H, Xing H, Yin Y, Li Z, Qi Y. Semantics-Preserving Adversarial Attacks on Event-Driven Stock Prediction Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(44):37645-37653. doi:10.1609/aaai.v40i44.41099

BibTeX
@article{Liu2026,
  author = {Liu, Aofan and Li, Haoxuan and Xing, Hongjian and Yin, Yuguo and Li, Zijun and Qi, Yiyan},
  title = {Semantics-Preserving Adversarial Attacks on Event-Driven Stock Prediction Models},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {44},
  pages = {37645--37653},
  doi = {10.1609/aaai.v40i44.41099}
}
Kostenlos starten →