This paper establishes a complexity hierarchy for shuffle operations used in card-based cryptography, classifying them by implementation difficulty and proving separations between these levels.

The paper addresses the privacy leak of speculative tool calls by proposing Speculative Tool Privacy Contracts, a runtime abstraction that ensures observation before commitment does not disclose user…

The paper addresses the privacy leak caused by speculative tool calls in language agents by proposing Speculative Tool Privacy Contracts, a runtime mechanism that restricts information leakage before…

The paper introduces AgentSecBench, a security evaluation framework that measures prompt injection, privacy leakage, and tool-use integrity in LLM agents by defining formal security games and testing…

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 develops a unified, cross-layer security framework for autonomous LLM agents operating in agentic commerce, identifying key attack vectors and proposing a layered defense architecture.

The paper introduces PTCG-Bench, a new benchmark using the Pokémon TCG to evaluate LLM agents' strategic decision-making and ability to self-evolve, finding that sustained self-evolution remains chall…

The paper proposes H-Elo, a Fully Homomorphic Encryption (FHE)-based system that enables private and secure matchmaking by keeping user rating values encrypted during the traditional rating update pro…

The paper introduces MyPhoneBench, a new framework that demonstrates that current phone-use agents often fail to respect user privacy, even when successfully completing simple tasks, primarily due to…

MemLineage introduces a novel, cryptographically-backed defense mechanism that enforces a chain-of-custody for LLM agent memory, preventing untrusted or poisoned state from justifying sensitive action…

The paper introduces a certified purity architecture that strengthens governance in cognitive workflow systems by replacing insufficient runtime checks with cryptographically attested structural guara…

This survey analyzes the unique security threats posed by complex, multi-agent AI systems and proposes Confidential Computing (CC) using Trusted Execution Environments (TEEs) as a hardware-rooted defe…

The paper proposes Sello, a novel protocol that allows an owner to reconstruct a tamper-evident and verifiable record of AI agent actions by having a trusted receiver sign and publish receipts of the…

SentinelAgent introduces a formal framework, the Intent-Preserving Delegation Protocol (IPDP), to secure federal multi-agent AI systems by verifying complex delegation chains against seven properties,…

Pepper is a novel, high-bandwidth anonymous broadcast protocol that achieves cryptographic sender anonymity and significantly improves messaging throughput compared to existing state-of-the-art system…

The paper proposes a trustless framework using dual-layer cryptographic commitments to solve the operator-gating problem in blockchain provenance trees, ensuring verifiable user attribution even when…

The paper proposes CAMP, a cross-turn privacy framework that mitigates Cumulative PII Exposure (CPE) in multi-turn LLM conversations by tracking and masking accumulated personal data across the entire…

This paper identifies and analyzes unintentional cross-user contamination (UCC), a failure mode where benign, scope-bound artifacts degrade the outcomes of different users in shared-state LLM agents,…

The paper introduces a stateful agent backdoor that allows malicious attacks to persist and execute incrementally across multiple sessions, significantly enhancing the threat model for LLM-based agent…

MaskClaw is an edge-side privacy arbitrator that protects sensitive data in GUI agent screenshots by combining local visual evidence, task-specific policies, and a skill-evolution mechanism.