Standing, Not Truth: Who May Say What About Whom in Agentic Selection

arXiv:2610.17952 · cs.CR · Submitted 2026-10-13 · Read on arXiv

cs.CR

Submitted: 2026-10-13

Updated: 2026-10-13

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

Signing the Transaction but Not the Decision: Whisper Attacks and a Binding Defense for AP2
A Survey on Open Information Extraction
MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning
Defeating Prompt Injections by Design
Aligning Provenance with Authorization: A Dual-Graph Defense for LLM Agents
The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck
Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees
AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution
MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
Influence Is Not Authority: When Causal Guardrail Signals Make Legitimate Tool Use Look Like an Attack in Tool-Using LLM Agents
AIRGuard: Guarding Agent Actions with Runtime Authority Control
PARSE: Provenance-Aware Retrieval Sanitization for Professional Domain LLM Agents
Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders
SoK: Security of Autonomous LLM Agents in Agentic Commerce
Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
TriShieldRAG: 3 Rings, One Blind Spot in Layered Defenses for Retrieval-Augmented Generation
AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
FAVA: Formal Authorization for Verified Agents with Evidence-Backed Permission Graphs
Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents

Related papers