This work proposes MAFIA, a query-only Memory Attack framework via probing and Factual Injection against Audit, tailored to this extended threat model, and introduces a placement strategy that ensures retrieval-competitive injection via memory probing, budget allocation, and scheduling.
Abstract
Memory-augmented LLM agents rely on rich context for long-horizon reasoning and acting, yet their memory modules expose a persistent attack surface for malicious records, making the study of memory poisoning threats imperative. However, existing query-only attacks often fail to remain effective in two realistic and prevalent settings: large-scale benign memory pools and active input auditing. Consequently, current approaches fall short when facing the dual challenges of high retrieval competitiveness and rigorous semantic checks. To overcome these limitations, we propose MAFIA, a query-only Memory Attack framework via probing and Factual Injection against Audit, tailored to this extended threat model. Specifically, MAFIA introduces: (1) a placement strategy that ensures retrieval-competitive injection via memory probing, budget allocation, and scheduling; and (2) a payload design that bypasses audits using compact factual cloaks, preserving malicious effects while maintaining high semantic similarity. Extensive evaluations reveal that MAFIA achieves up to a 90.7% attack success rate while suppressing audit detection from a peak of 83.3% to at most 7.4%, exposing critical vulnerabilities across agentic memory systems. Code will be made publicly available at https://github.com/JiamingChen1234/MAFIA.
The first extraction attack designed for this threat model, SPORE decouples the adversarial command from retrieval anchors by persisting the command in short-term memory and emitting semantically pure anchors in tool responses, demonstrating that memory isolation alone is insufficient and call for reexamining tool-side trust boundaries in agent architectures.
This work proposes InjecMEM, a novel memory injection attack paradigm that requires only a single interaction to steer later responses of related queries toward a pre-specified output and achieves reliable topic-conditioned retrieval and targeted generation.
Hanling Tian, Gengyu Zhang, Zeyang Sha et al.· 3 citations
LLM agents that operate over many turns accumulate facts in an external memory store and reuse them as premises for downstream reasoning. A hallucinated fact written at one step therefore persists as a false premise for every subsequent step, a failure mode we call memory contamination. Existing memory management addresses retrieval and capacity but not write-time correctness; this admission problem cannot be solved by utility- or recency-based criteria, and uncontrolled contamination compounds across long trajectories. We propose ConsistencyGate, a write-time admission gate that, before committing a candidate fact m extracted from context c, queries the LLM K times for a soft support score and admits m only when the average exceeds a threshold. The mechanism is model-agnostic, requires no fine-tuning, and reduces to a single forward pass in a log-probability variant for latency-sensitive deployments. To measure the effect on natural data, we construct two real-conversation benchmarks (LoCoMo-Contam and MSC-Contam) by planting controlled single-detail corruptions in long-term conversations from LoCoMo and MSC, and complement them with a structured synthetic corpus (MemContam) that isolates a near-oracle upper bound. Across four LLM backbones, ConsistencyGate reduces contamination on every benchmark relative to a write-everything baseline, with the cost concentrated on facts that are stated only implicitly in the source context. We release all three benchmarks together with the gate implementation.
This paper does an audit of defense mechanisms under jailbreak attacks on locally deployed models by tracing each failure back to the specific assumption it relies on.
Att2RAG is presented, a double-condition framework for knowledge poisoning attacks on RAG systems that decomposes a successful poisoning event into a retrieval condition and a generation condition, and casts poisoning as maximizing attack success subject to satisfying both conditions.
Zhize Hao· Poster Volume 0008 The 2026...· 0 citations
This paper introduces MemCollusion, an automated red-teaming framework for constructing collusive memory poisoning attacks, and develops MoltLab, a controlled research reproduction of Moltbook, in which crafted platform content must first be observed and distilled into persistent memory before influencing the agent's behavior in a separate session.
Zheng Lin, Yuzhen Huang, Zhenxing Niu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
