Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees

• URL: http://arxiv.org/abs/2606.24322v1
• Date: Tue, 23 Jun 2026 08:57:50 GMT
• Title: Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees
• Abstract summary: LLM agents increasingly rely on persistent long-term memory, which creates a critical vulnerability that we study here: memory poisoning.<n>An adversary can store untrusted content in one session that later steers a consequential action, such as a payment, a setting change, or data exfiltration.<n>Existing defenses base a memory item's authority to act on either its content (detection or trust-scoring) or its derivation history (lineage)<n>An attacker can launder an untrusted origin through three channels specific to LLM agents: the agent's own summarization, a trusted-tool echo, and manufactured corroboration
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM agents increasingly rely on persistent long-term memory, which creates a critical vulnerability that we study here: memory poisoning. An adversary can store untrusted content in one session that later steers a consequential action, such as a payment, a setting change, or data exfiltration, in a future session. Existing defenses base a memory item's authority to act on either its content (detection or trust-scoring) or its derivation history (lineage). We show that both signals are malleable. An attacker can launder an untrusted origin through three channels specific to LLM agents: the agent's own summarization, a trusted-tool echo, and manufactured corroboration. Each makes the content look benign and breaks or flips its derivation edge to ``trusted.'' We formalize malleability for the memory write-retrieve-act pipeline and prove a machine-checked separation theorem. No content- or lineage-based defense is sound under laundering (T1), write-time origin binding is necessary (T2), and non-malleable origin-bound authority with Sybil-resistant corroboration-gated elevation is sufficient (T3). Our construction, TMA-NM (Tamper-evident Memory Authority, Non-Malleable), instantiates non-malleable information-flow control (IFC) for LLM-agent memory. A cross-defense, cross-attack, and cross-model benchmark over eight frontier models shows that existing defenses fail exactly where the theory predicts (up to 68% laundering attack-success), while TMA-NM reaches 0% attack success on both direct and laundering attacks across all models and channels, at full legitimate utility. We release the benchmark, harness, and machine-checked TLA+ models to support reproducibility.

Related papers

• LMSM: LLM Security Framework Inspired by Linux Security Modules [56.93644694627783]
  Large language models (LLMs) are increasingly deployed with layered defenses, yet malicious prompts can still bypass them.<n>We present Language Model Security Modules (LMSM), a security framework that adapts the separation behind Linux Security Modules (LSM) to LLM serving.
  arXiv  Detail & Related papers  (2026-08-26T12:13:05Z)
• CyberLLM: A Multi-Agent LLM Framework for Autonomous Detection and Guarded Response in Automotive Cybersecurity [22.68559728326395]
  CyberLLM is a framework that autonomously detects vulnerabilities and executes remediations under a formal, runtime safety guard.<n>Decision agents aggregates findings, tags them with a human-centric asset taxonomy, and selects a tiered response.<n>A symmetric attack pipeline generates and replays exploits so both sides can be exercised on the same scenarios.
  arXiv  Detail & Related papers  (2026-08-06T23:39:13Z)
• MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents [20.418842618724607]
  We propose a comprehensive benchmark and analysis framework featuring 1227 hand-validated cases across four attack types.<n>We introduce a three-tier taxonomy: (L1) direct single-record corruption, (L2) compositional multi-record corruption and (L3) context-triggered dormant corruption.<n>Our evaluations reveal a distinct defense frontier: while baseline write-time defenses, such as consistency checks, substantially suppress direct L1 attacks, they fail to reliably suppress L2 and L3 attacks.
  arXiv  Detail & Related papers  (2026-07-16T07:19:33Z)
• AgentSecBench: Measuring Prompt Injection, Privacy Leakage, and Tool-Use Integrity in LLM Agents [0.2864713389096699]
  We introduce AgentSecBench as an empirical instantiation of a formal security framework for this problem.<n>It defines three games-instruction-integrity, retrieval-confidentiality, and capability-integrity-under a common notion of intent-to-execution noninterference with permitted leakage.<n>It represents an application policy as a projection onto authorized observations and capabilities, distinguishes prompt annotations from enforcing projections, and measures both adversarial advantage and whether a defense closes the relevant model-visible channel before generation.
  arXiv  Detail & Related papers  (2026-05-25T18:53:22Z)
• MemLineage: Lineage-Guided Enforcement for LLM Agent Memory [3.058164432275431]
  We introduce MemLineage, a defense for LLM agent memory that attaches cryptographic provenance and LLM-mediated lineage to every entry.<n>Recent and concurrent work shows that untrusted content can be written into persistent agent state and re-enter later sessions as an instruction.<n>MemLineage treats this as a chain-of-custody problem rather than a filtering problem.
  arXiv  Detail & Related papers  (2026-05-14T06:07:54Z)
• The Misattribution Gap: When Memory Poisoning Looks Like Model Failure in Agentic AI Systems [1.0262304700896199]
  We formalize emphSemantic Norm Drift (SND) as a third path to agent misconduct.<n>In SND, a policy-formatted document enters a shared vector store through normal uploads and later reappears as trusted system context.<n>Counterfactual Composition Testing identifies the causal entry with 87.5% accuracy and zero false positives.
  arXiv  Detail & Related papers  (2026-05-12T20:21:47Z)
• TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning [60.68349524623048]
  Decompositional jailbreaks pose a critical threat to large language models.<n>We present TwinGate, a stateful dual-encoder defense framework.<n>We construct a comprehensive dataset of over 3.62 million instructions spanning 8,600 distinct malicious intents.
  arXiv  Detail & Related papers  (2026-04-30T13:44:01Z)
• TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models [19.148124494194317]
  We propose TraceGuard, a process-guided security framework that transforms small-scale models into robust reasoning firewalls.<n>Our approach treats the reasoning trace as an untrusted payload and establishes a defense-in-depth strategy.<n>We demonstrate robustness against adaptive adversaries in a grey-box setting, establishing TraceGuard as a viable, low-latency security primitive.
  arXiv  Detail & Related papers  (2026-03-02T22:19:13Z)
• Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections [57.64370755825839]
  Self-evolving agents update their internal state across sessions, often by writing and reusing long-term memory.<n>We study this risk and formalize a persistent attack we call a Zombie Agent.<n>We present a black-box attack framework that uses only indirect exposure through attacker-controlled web content.
  arXiv  Detail & Related papers  (2026-02-17T15:28:24Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain [82.98626829232899]
  Fine-tuning AI agents on data from their own interactions introduces a critical security vulnerability within the AI supply chain.<n>We show that adversaries can easily poison the data collection pipeline to embed hard-to-detect backdoors.
  arXiv  Detail & Related papers  (2025-10-03T12:47:21Z)
• A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory [31.673865459672285]
  Large Language Model (LLM) agents use memory to learn from past interactions.<n>An adversary can inject seemingly harmless records into an agent's memory to manipulate its future behavior.<n>A-MemGuard is the first proactive defense framework for LLM agent memory.
  arXiv  Detail & Related papers  (2025-09-29T16:04:15Z)
• Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning [58.57194301645823]
  Large language models (LLMs) are increasingly integrated into real-world personalized applications.<n>The valuable and often proprietary nature of the knowledge bases used in RAG introduces the risk of unauthorized usage by adversaries.<n>Existing methods that can be generalized as watermarking techniques to protect these knowledge bases typically involve poisoning or backdoor attacks.<n>We propose name for harmless' copyright protection of knowledge bases.
  arXiv  Detail & Related papers  (2025-02-10T09:15:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.