Researchers expose prompt injection risks in financial AI agents
ArXiv study warns that agentic LLMs with local machine access can leak credentials and redirect transactions via prompt injection—a threat beyond standard jailbreak tests.
Latest
1 more from arXiv: AI + Accounting
Research warns AI agents risk credential theft, financial fraud via prompt in...
Academic study reveals personal AI agents with elevated privileges—like OpenClaw—vulnerable to prompt injection attacks that could leak credentials or redirect financial transactions, exposing gaps...
AI enables scalable fraud detection across accounting teams
CPA Practice Advisor explores how AI infrastructure now allows accounting firms to deploy multi-person fraud oversight at scale, shifting from manual review to automated vigilance.
Fake SOC 2 Reports Expose AI-Driven Compliance Fraud in Accounting
The Accounting Podcast investigates allegations that compliance startup Delve sold hundreds of fake SOC 2 reports using AI-fabricated auditor conclusions, while exploring how accountants are actual...
Graph Neural Networks Improve Anti-Money Laundering Detection in Transaction ...
Researchers propose LineMVGNN, a spectral graph neural network designed to detect suspicious transactions and accounts in AML systems with improved accuracy over rule-based methods while maintainin...