paperFebruary 2026Unreviewed

PromptShield: LoRA-Based Parameter-Efficient Refusal Alignment for Election-Targeted Adversarial LLM Attacks

Nishmitha M R, Tejakshi N S, Anshu Sharma, Kiran, A. M, Karan

IEEE International Conference on Circuits and Systems for Communications

Abstract

Large language models (LLMs) are increasingly deployed in public-facing information systems, where their misuse poses serious risks in high-stakes domains such as democratic elections. Despite extensive safety alignment, contemporary LLMs remain vulnerable to adversarial “jailbreak” prompting, enabling the generation of election-related misinformation, voter suppression narratives, and procedural manipulation. Recent election cycles have documented hundreds of verified instances of LLM-assisted

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@inproceedings{r2026promptshield,
  title = {{PromptShield: LoRA-Based Parameter-Efficient Refusal Alignment for Election-Targeted Adversarial LLM Attacks}},
  author = {Nishmitha M R and Tejakshi N S and Anshu Sharma and Kiran and A. M and Karan},
  year = {2026},
  month = feb,
  booktitle = {IEEE International Conference on Circuits and Systems for Communications},
  doi = {10.1109/ICCSC67078.2026.11468767},
  url = {https://www.semanticscholar.org/paper/2860efddd9ce86ac18c5dbfd7c427c08e6bed6a2}
}