AI ethics evidence index Search
Source-linked daily record
Evidence record 14482 · automatically gathered

Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks

Large Language Models (LLMs) have been widely applied in high-stakes decision-making scenarios such as corporate strategy, and users are increasingly relying on their outputs. However, the deep integration of open-source model sharing ecosystems with LLM-powered critical decision-making applications also introduces critical risks: if an attacker can manipulate the model's cognitive stance, they can indirectly influence the judgments and actions of downstream decision-makers. This paper defines s

Record details

Published: 28 July 2026
Source: arXiv cs.LG
Category: Research
Topics: Bias & fairness
Retrieved: 29 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Bias & fairness

Moralizing metrics: Discourses of data and equity in California's public health response to COVID-19

Big Data & Society · 28 July 2026

Shared topic: Bias & fairness

Fairness Interventions in Classification: A Study on AI Explainability

arXiv cs.CY · 28 July 2026

Shared topic: Bias & fairness

A Computational Ethical Framework for Financial Digital Phenotyping for Mental Health

arXiv cs.CY · 28 July 2026

Shared topic: Bias & fairness

Private Again: AI Agents Restore Anonymity---Foreclosing Discrimination and Its Proof

arXiv cs.CY · 28 July 2026

Shared topic: Bias & fairness

Beyond the Post Hoc User Study: Modeling Visual Decision-Making with Active Inference

arXiv cs.HC · 27 July 2026

Shared topic: Bias & fairness

Inspect India Evals: An Open Benchmarking Framework for Evaluating Large Language Models in the Indian Linguistic and Cultural Context

arXiv red teaming query · 28 July 2026

How to cite this record

ethics.ai (28 July 2026), “Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks,” evidence record 14482, https://ethics.ai/record/14482 (originally published by arXiv cs.LG).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.