This paper proposes a unified, lifecycle-centric framework and a detailed taxonomy to survey and analyze novel, finance-specific attack surfaces and vulnerabilities in AI systems used within the finan…

The paper proposes a novel structural invariant approach, derived from the economic constraints of fraud, that amplifies weak, low-precision signals into highly accurate fraud detections without requi…

The paper evaluates graph-context LLM defenders against multi-round, adaptive fraud attacks, finding that while graph context improves early safety, it significantly increases benign over-refusal due…

The paper demonstrates that current defenses against malicious fine-tuning of foundation models are insufficient because they only address fixed attacks, and introduces a unified adaptive attack that…

The paper establishes a standardized security assessment framework and develops a multi-layered defensive system, demonstrating that systematic testing and external defenses are crucial for safe LLM d…

The paper introduces MEV non-interference, a formal security notion, to ensure that composing new smart contracts in DeFi does not increase the maximal extractable value, thereby providing a formal fo…

The paper proposes FinSec, a novel four-tier security detection framework, to robustly identify complex financial risks and suspicious dialogue patterns in LLM-powered financial agents, achieving stat…

The paper introduces the Lean-Agent Protocol, a formal verification platform that uses Lean 4 theorem proving to ensure agentic AI actions in finance are mathematically compliant with complex regulati…

The paper analyzes and documents various double-dip reward abuse attacks that exploit flaws in how cashback and reward engines handle transaction refunds, proposing formal invariants and defensive alg…

The paper proposes RESSAP, a novel ensemble framework that significantly enhances the robustness of machine learning classifiers against adversarial evasion attacks by combining feature selection, ens…

The paper proposes a novel nine-dimension risk assessment framework for institutional DeFi adoption, significantly enhancing existing methodologies by incorporating novel dimensions like composability…

The paper introduces the concept of 'authenticity debt'—the institutional liability from deploying unverified AI content—and proposes a layered reference architecture combining cryptographic provenanc…

The paper introduces the concept of 'authenticity debt'—the institutional liability from deploying unverified AI content—and proposes a layered reference architecture combining cryptographic provenanc…

The paper demonstrates that large language models (LLMs) exhibit measurable, controllable biases toward specific assets like Bitcoin, identifying an internal feature that can causally shift portfolio…

This paper addresses the vulnerability of existing LLM safety monitors to adaptive attackers and proposes activation watermarking, a technique that significantly improves detection robustness against…

This paper proposes a comprehensive framework utilizing AI and machine learning to enhance cybersecurity and mitigate fraud risks in the emerging field of cardless artificial intelligence banking.

The paper introduces Dynamic Sharded Federated Learning (DSFL), a secure aggregation framework that significantly reduces communication overhead and enhances update verification for cross-institution…

This paper develops a formal economic framework to assess the security of VDF-based randomness beacons, demonstrating that many proposed delays are economically insecure due to rational, profit-motiva…

The paper proposes CyberAId, a hybrid multi-agent system designed to enhance cybersecurity for financial institutions by integrating specialized LLM subagents with existing SIEM/XDR telemetry, address…

The paper introduces a queueing-theoretic framework to model dynamic cyber-attack surfaces, developing an adaptive reinforcement learning defense policy that significantly reduces active vulnerabiliti…