ZK-Value introduces a practical, scalable zero-knowledge system for calculating data valuations (Shapley values) in data marketplaces, significantly reducing proving time while maintaining high accura…

ShaplEIG introduces a Bayesian experimental design framework to efficiently and adaptively estimate Shapley values by minimizing the number of required costly function evaluations.

VeriX-Anon is a multi-layered framework that provides mathematically verifiable assurance that outsourced data anonymization (k-anonymization) was executed correctly, achieving high detection rates ag…

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 a class of steganographic exfiltration attacks against vector databases by hiding data within embeddings, and proposes VectorPin, a cryptographic provenance protocol to detect s…

The paper proposes Proof of Useful Attestation (PoUA), a consensus mechanism that weights validator vote power not just by staked capital, but also by a reputation score earned through performing vali…

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…

RAGShield introduces a novel, pattern-based defense system that accurately detects subtle numerical claim manipulation in government RAG systems, overcoming the inherent blind spot of embedding-based…

The paper demonstrates that token rankings provide a unique, unforgeable signature for language models, and proposes an API restriction that allows for signature presentation without leaking model par…

The paper proposes SubPopMark, a novel subpopulation-driven framework that injects harmless, verifiable markers into distilled datasets to prevent copyright infringement and data leakage.

This paper analyzes the reliability of efficient membership inference attack (MIA) evaluation methods, demonstrating that standard aggregation techniques introduce biases that compromise accurate vuln…

SAGE introduces a novel counterfactual-aware negative harvesting ensemble that accurately identifies fraudulent activity by robustly distinguishing it from legitimate, rare user behaviors in unlabeled…

The paper demonstrates that the current per-token billing model for LLMs is susceptible to systematic overcharging because auditing frameworks must rely on evidence provided by the very companies that…

The paper demonstrates that the current per-token billing model for LLMs is susceptible to systematic inflation because auditing frameworks must rely on evidence provided by the service provider, crea…

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…

The paper proposes PatentXAI, a scalable framework that uses graph-conditioned Shapley values to fairly attribute product profit among thousands of patents, significantly improving computational tract…

MemMark introduces a state-evolution attribution watermark that embeds owner-controlled signals into latent memory-write decisions, enabling robust provenance tracking for agent memory even when all t…

RogueMerge introduces a unified framework to robustly attack LLM model merging by addressing the challenges of autoregressive decoding, unknown merging configurations, and prompt generalization, signi…

The paper proposes a new evaluation framework showing that, under realistic conditions, Membership Inference Attacks (MIAs) are weak privacy threats, suggesting that relying on them as a primary priva…

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…