PwC's AI systems are producing hallucinated leadership reports with fabricated details and false information, exposing risks in deploying large language models for audit and compliance work without...
Researchers combine gradient boosting, graph features, SHAP explanations, and bounded LLM agents to build auditable fraud detection that scales with transaction volume while remaining reviewable fo...
Researchers propose robust financial statement fraud detection framework using LLMs that addresses overfitting in prior work by testing generalization across companies and time periods, advancing f...
Researcher proposes verifiable event timeline for autonomous commerce agents with tamper-evident auditability and fraud detection, addressing gaps in AP2 and ACP protocols.
Researchers propose using misinformation detection and explanation techniques to assist financial auditors in identifying material misstatements in balance sheets, income statements, and cash flow ...
Researchers develop LightGBM-based detection system with TreeSHAP attribution to identify money mule accounts at scale, combining 280 transactional and behavioral features for explainable fraud pre...
Research paper argues that AI agent failures stem from weak context engineering—poor instructions, tools, and guardrails—not agent architecture alone, with implications for reliable accounting auto...
Academic research proposes XAI-enhanced Isolation Forest model for banking transaction anomaly detection, addressing compliance teams' need for interpretable fraud alerts over opaque rule-based sys...
PREF-Gate framework applies provenance-constrained evidence fusion to relational fraud detection, addressing validity issues in neighborhood risk assessment for financial graph analysis.
Researchers propose QLoRA-tuned LLMs for telecom fraud detection with blockchain-linked audit trails, showing improvements over zero-shot prompting but comparable to cheaper centralized ensembles.
Tax professionals' AI adoption for research jumped to 60% weekly use in 2026, but the trend has a dark side: employees are using AI to fabricate expense receipts, a phenomenon called 'revenge spend...
The Accounting Podcast reports AI receipt fraud has exploded from nonexistent in early 2025 to accounting's fastest-growing compliance crisis, with 70% of current fraud detections now involving AI-...
Researchers propose diffusion-guided learning to improve fraud detection in transaction networks despite sparse labels and imbalanced data, addressing real-world challenges in financial system secu...
AI-generated fake receipts have become the primary method for expense fraud, replacing template-based approaches, according to Accounting Today reporting.
IRS advisory committee recommends sustained funding for AI tools while implementing preparer regulation and fraud prevention safeguards in tax administration.
An agentic AI system tasked with audit verification hallucinated and created false documentation three times, highlighting critical safety gaps in deploying autonomous AI agents in accounting workf...
Academic research reveals tool-augmented LLM agents used in accounting contexts are vulnerable to prompt injection attacks through multiple surfaces beyond tool outputs, challenging current securit...
Capterra survey of 500 US accounting managers finds 89% see ROI from AI tools in chatbots, data entry, and fraud detection, yet 52% experienced recent data breaches and most lack clear AI data-hand...
YC-backed founder built automation for forensic accounting tasks, reducing manual work by 62% for his father's practice—demonstrating practical AI/accounting convergence.
UK tax authority HMRC will use AI from a British tech company to identify fraud and errors in tax returns, signaling regulatory adoption of AI for compliance and revenue protection.