AgentSocialBench demonstrates that privacy preservation is fundamentally harder in human-centered agentic social networks than in single-agent cases due to cross-domain coordination pressures and an abstraction paradox where privacy instructions increase discussion of sensitive information.
Title resolution pending
7 Pith papers cite this work, alongside 7 external citations. Polarity classification is still indexing.
7
Pith papers citing it
7
external citations · OpenAlex
citation-role summary
background 4
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 4polarities
background 4representative citing papers
AgentThread analyzes five agent protocols with formal TLA+ invariants and SDK tests, reporting 35 specification findings, 80 implementation tests, 30 composition-only failures, and a cross-protocol responsibility gap in security enforcement.
A data-centric survey finds that only information-flow control covers compositional and cross-session leakage in LLM agents and that no single benchmark tests an agent across all its data surfaces under one policy.
The paper introduces a taxonomy of security risks in cloud-hosted tool-enabled AI agents arising mainly from over-privileged tools and authority leakage, supported by scenarios, mitigations, and a small experiment.
A survey providing a taxonomy of TEE platforms, an agent-centric threat model, and open challenges for applying confidential computing to secure agentic AI systems.
FinSec is a multi-stage detection system for financial LLM dialogues that reaches 90.13% F1 score, cuts attack success rate to 9.09%, and raises AUPRC to 0.9189.
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
citing papers explorer
-
AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks
AgentSocialBench demonstrates that privacy preservation is fundamentally harder in human-centered agentic social networks than in single-agent cases due to cross-domain coordination pressures and an abstraction paradox where privacy instructions increase discussion of sensitive information.
-
Formal Security Analysis of Agent Protocol Composition
AgentThread analyzes five agent protocols with formal TLA+ invariants and SDK tests, reporting 35 specification findings, 80 implementation tests, 30 composition-only failures, and a cross-protocol responsibility gap in security enforcement.
-
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents
A data-centric survey finds that only information-flow control covers compositional and cross-session leakage in LLM agents and that no single benchmark tests an agent across all its data surfaces under one policy.
-
Security Risks in Tool-Enabled AI Agents: A Systematic Analysis of Privileged Execution Environments
The paper introduces a taxonomy of security risks in cloud-hosted tool-enabled AI agents arising mainly from over-privileged tools and authority leakage, supported by scenarios, mitigations, and a small experiment.
-
When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI
A survey providing a taxonomy of TEE platforms, an agent-centric threat model, and open challenges for applying confidential computing to secure agentic AI systems.
-
Conversations Risk Detection LLMs in Financial Agents via Multi-Stage Generative Rollout
FinSec is a multi-stage detection system for financial LLM dialogues that reaches 90.13% F1 score, cuts attack success rate to 9.09%, and raises AUPRC to 0.9189.
-
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.