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 evaluates LLM-based simulators for generating differentially private synthetic data, finding that while they show promise for utility, they suffer from significant distribution drift due to…

The paper proposes RPSG, a method that uses private seeds and differential privacy to generate highly realistic and strongly privacy-preserving synthetic data replicas of private text for LLMs.

The paper systematically analyzes 36 existing and proposed digital payment system designs to identify recurring patterns, technical trade-offs, and implementation challenges relevant for future Centra…

This paper analyzes the x402 payment protocol, revealing systemic vulnerabilities in state synchronization and signature design that allow attackers to exploit payment systems for resource leakage in…

This paper analyzes the x402 payment protocol, revealing critical synchronization and security flaws that allow attackers to exploit payment systems and force merchants to subsidize compute costs.

The paper proposes a novel framework that enables multiple institutions to jointly train a synthetic genomic data generator without revealing their raw data, thereby facilitating large-scale, privacy-…

This paper proposes two post-processing techniques, random selection and linear combination, to construct a model that satisfies any desired differential privacy level without retraining, given a set…

DPDSyn improves differentially private dataset synthesis by training a differentially private AI model on the original private data, which is then used to generate synthetic datasets that maintain hig…

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 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 argues that Agentic AI fundamentally breaks the historical security tradeoff between deception fidelity and scale, necessitating a shift from authenticating actors to evaluating actions.

The paper systematizes the interaction between autonomous AI agents and blockchain platforms using a bidirectional trust framework, identifying significant gaps in current standards and proposing a ta…

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…

The paper investigates how users perceive and utilize security and privacy transparency in consumer-facing generative AI, finding that users rely on proxies like popularity and require actionable, tru…

This paper reviews recent EU AI regulatory documents to clarify definitions and synthesize current provisions regarding security, privacy, and autonomous agentic AI.

BlindMarket is a zero-trust framework that enables the verifiable, confidential, and traceable distribution of hardware IP cores between vendors and users.

The paper proposes replacing individual agent autonomy with a structured 'social contract' and institutional Separation of Power (SoP) to mitigate systemic failures and deceptive behavior in multi-age…

The paper introduces DPrivBench, a new benchmark to test whether large language models (LLMs) can automate the complex reasoning required to verify differential privacy guarantees for algorithms.