The paper introduces Consent Integrity, a new property for LLM agent approval, ensuring that the action shown to a human for approval is verifiably linked to the actual executed action, even when the…

This paper separates three mechanisms contributing to pipeline safety in multi-agent large language models and introduces a controlled contrast design to evaluate their impact.

The paper proposes a robust causal decision framework to measure advertising incrementality despite multiple sources of privacy-induced signal degradation, providing certified decisions on the strengt…

This paper characterizes the impact of ETSI Decentralized Congestion Control (DCC) on age of information (AoI) for vehicle-to-infrastructure updates, revealing a hyperbolic density dependence and prop…

This paper compares the effectiveness of classical and neural speech codecs using P.808 and P.800 DCR tests in crowdsourced and conventional evaluations. It proposes suitable screening methods for imp…

The paper proposes Proof-Carrying Agent Actions (PCAA), a runtime-neutral governance model that uses action certificates to consistently track and authorize high-risk actions across diverse and hetero…

The paper proposes and tests a novel, non-security 'Recuse Signal'—an in-band signal—to allow operators to tell autonomous LLM agents to voluntarily withdraw access, demonstrating that compliant agent…

The paper introduces Score Broadcast and Decorrelation (SBD), a general theoretical framework that unifies broadcast-based credit assignment across various differentiable loss functions by leveraging…

This paper characterizes the optimal allocation for public-good provision with local privacy constraints.

This paper proposes a value-based DCC method for Intelligent Transport Systems to maintain channel load while retaining more high-value objects.

The paper introduces Acceptance Cards, a rigorous four-diagnostic standard, to provide a comprehensive and reliable evaluation protocol for claims of safe fine-tuning defenses.

The paper argues that LLM agent security is fundamentally an agent-human interaction (AHI) problem, demonstrating that industry practices rely on human-centric mechanisms while academic research focus…

The SAFE approach enhances fault-tolerant trust management in VANETs by ensuring vehicles send updated feedback reports before leaving a witness area, significantly reducing erroneous penalization of…

The paper demonstrates that the order and content of external information (the 'feed') an LLM agent consumes before making a decision can significantly and causally steer its final choice, often overr…

The paper demonstrates that the sequence and composition of external information (the 'feed') an LLM agent consumes can significantly and causally steer its final decisions, often overriding its defau…

This paper introduces Distributed Quorum Signature (DQS), a new primitive built from ordinary digital signatures and approval broadcasts, enabling constant-size quorum signatures in distributed system…

The paper proves that standard runtime enforcement mechanisms cannot detect systematic behavioral drift in autonomous agents, proposing a new Invariant Measurement Layer (IML) that restores observabil…

Aegon is a new protocol that provides an auditable, tamper-evident infrastructure for tracking AI content licensing transactions and compliance receipts.

The paper proposes a TEE-based architecture that enables external, auditable verification of AI-assisted grant evaluations without exposing the proprietary model, scoring logic, or intermediate reason…