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…

This paper investigates how Generative AI enables scalable, hyper-realistic fraud in Chinese e-commerce by fabricating product defect evidence, proposing new defense mechanisms like verifiable materia…

The paper introduces a formal Risk-Cost Model (RCM) to provide an economically grounded and mathematically rigorous framework for adaptive authentication in high-stakes financial systems.

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

GenDetect introduces a novel framework to rapidly generalize detection rules from single observed DeFi exploits, significantly improving resilience against subsequent, similar 'Imitative Attack Cascad…

The paper proposes a dual-regime architecture combining Bernoulli CUSUM and asymmetric scoring to significantly improve trust fraud detection in sparse rating networks, achieving superior performance…

UniDetect is a novel LLM-driven method that detects cross-chain cryptocurrency fraud by generating generalized transaction summaries, significantly outperforming existing detection techniques across m…

The paper demonstrates that autonomous web agents are highly susceptible to social-engineering attacks, leaking critical PII even when they internally flag a site as suspicious, necessitating output-l…

The paper demonstrates that autonomous web agents are highly susceptible to social-engineering attacks, leaking critical PII even when they internally flag a site as suspicious, necessitating output-l…

The paper introduces ARCANE, a Bayesian network framework for cross-campaign cyber attribution, finding that while aggregating telemetry improves identification, structural feature limitations prevent…

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…

SCAFDS introduces a novel, seven-stage graph attention system that models fraud propagation using co-occurrence edge features and generates forensically traceable SAR narratives, significantly improvi…

The paper introduces the Sequential Triply Robust (STR) estimator, a method that corrects for multiple systematic biases (authorization, reporting, delay, and corruption) in chargeback labels to achie…

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 demonstrates that LoRA adapters can be backdoored via data poisoning, showing the backdoor generalizes at the token feature level, and proposes robust behavioral and weight-level detectors f…

This paper demonstrates that LoRA adapters can be backdoored via data poisoning, showing that the resulting backdoor generalizes at the token feature level, and proposes robust behavioral and weight-l…

The paper identifies a universal, statistically predictable distribution (Mandelbrot) governing LLM outputs, enabling a highly efficient, model-agnostic scoring primitive for provenance and quality as…

The paper proposes DynaHug, a dynamic analysis technique that uses machine learning to detect malicious pre-trained machine learning models by learning the runtime behaviors of benign models, achievin…

This paper analyzes the Solana Rug Pull ecosystem by creating a large-scale, manually verified dataset of fraudulent tokens, identifying three key behavioral patterns, and characterizing the resulting…

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…