arXiv subjects

Kenneth See

Publications and source records attributed to Kenneth See.

3 recordsLinked to original sources

arXiv2026

Compliance-Aware Agentic Payments on Stablecoin Rails

Agentic payment systems extend delegated action to financial transfers, but scaling them on stablecoin rails in regulated settings requires safeguards that remain effective when humans are not continuously in the loop. We present a compliance-aware architecture that combines x402-style, signature-based payment authorisation and relayed execution with programmable compliance embedded as an on-chain guardrail via a policy wrapper and policy manager coordinating modular checks. By enforcing compliance at the point of execution, rather than as a separate off-chain workflow, the approach preserves low-friction settlement when conditions are satisfied, records transaction-linked on-chain attestations, and supports structured resolution when requirements are pending.

cs.CR↗

arXiv2025

Anticipate, Simulate, Reason (ASR): A Comprehensive Generative AI Framework for Combating Messaging Scams

The rapid growth of messaging scams creates an escalating challenge for user security and financial safety. In this paper, we present the \textit{Anticipate, Simulate, Reason} (ASR) generative AI framework to enable users to proactively identify and comprehend scams within instant messaging platforms. Using large language models, ASR predicts scammer responses and delivers real-time, interpretable support to end-users. We also develop ScamGPT-J, a domain-specific language model fine-tuned on a new, high-quality dataset of scam conversations covering multiple scam types. Thorough experimental evaluation shows that the ASR framework substantially enhances scam detection, particularly in challenging contexts such as job scams, and uncovers important demographic patterns in user vulnerability and perceptions of AI-generated assistance. Our findings reveal a contradiction where those most at risk are often least receptive to AI support, emphasizing the importance of user-centered design in AI-driven fraud prevention. This work advances both the practical and theoretical foundations for interpretable and human-centered AI systems in combating evolving digital threats.

cs.HC↗

arXiv2024

ScamGPT-J: Inside the Scammer's Mind, A Generative AI-Based Approach Toward Combating Messaging Scams

The increase in global cellphone usage has led to a spike in instant messaging scams, causing extensive socio-economic damage with yearly losses exceeding half a trillion US dollars. These scams pose a challenge to the integrity of justice systems worldwide due to their international nature, which complicates legal action. Scams often exploit emotional vulnerabilities, making detection difficult for many. To address this, we introduce ScamGPT-J, a large language model that replicates scammer tactics. Unlike traditional methods that simply detect and block scammers, ScamGPT-J helps users recognize scam interactions by simulating scammer responses in real-time. If a user receives a message that closely matches a ScamGPT-J simulated response, it signals a potential scam, thus helping users identify and avoid scams more effectively. The model's effectiveness is evaluated through technical congruence with scam dialogues and user engagement. Our results show that ScamGPT-J can significantly aid in protecting against messaging scams.

cs.HC↗