The cost of this failure mode using plainly worded false assertions generated in a single pass, with no instruction, trigger, or retriever optimization is measured, and bounded occupancy constraints at retrieval rather than additive provenance penalties are argued.
Abstract
Persistent memory makes false information durable: once a false statement is stored, it can be retrieved into future sessions that match it. We measure the cost of this failure mode using plainly worded false assertions generated in a single pass, with no instruction, trigger, or retriever optimization. Poisoning 1.2% of a LongMemEval corpus reduces accuracy from 0.850 to 0.300. A four-stage write-time screening pipeline that reaches 0.832 recall on indirect prompt injection while flagging 1.5% of trigger-word-laden benign text rejects 0 of 360 poisoned memories. We argue this exposes a boundary of content-only screening: distinguishing a false assertion from a true one generally requires external grounding beyond the text itself. We then evaluate provenance-weighted retrieval. The shipped weight is statistically indistinguishable from no defense (p=0.80), while a stronger weight recovers utility only by excluding untrusted content. In a mixed-provenance corpus where untrusted content is mostly benign, accuracy rises from 0.3167 to 0.7000; when the answer-bearing evidence itself arrives untrusted, evidence recall falls to zero and accuracy to 0.0417. Under the measured similarity regime, the additive provenance term has no usable setting: a weight strong enough to resist query-shaped poison is also strong enough to suppress legitimate untrusted evidence. We therefore argue for bounded occupancy constraints at retrieval rather than additive provenance penalties, and release the harnesses, corpora, and aggregate run reports.
The one signal that separates an attack from legitimate niche ingestion -- a query's demand -- is invisible before retrieval, which is also the escape: a retrieval-time detector that observes demand catches 100% of the attacks at the same 1% false-positive rate.
Retrieval-Augmented Generation (RAG) grounds large language models in external corpora, but implicit trust in retrieved documents creates a critical attack surface: PoisonedRAG shows that a handful of crafted passages can dominate dense retrieval and steer generation toward attacker-chosen answers. We present the Tri-Layer Sieve, a middleware defense that sanitizes retrieved evidence through cross-embedding-space clustering with an independent judge model, structural filtering of trigger-payload artifacts, and LLM consistency verification. The design exploits a key weakness of retrieval-stage poisoning: a single document must satisfy one embedding geometry, one internal Trigger-Payload structure, and one generation objective - rarely all three simultaneously, a fragility that persists even against an adaptive attacker who paraphrases around it. On Natural Questions, HotpotQA, and MS-MARCO with Contriever retrieval (k=50), the Sieve reduces black-box Attack Success Rate from 67.0/87.0/64.0% to 3.0/14.0/4.0%, mitigates white-box HotFlip attacks from ~74% to 27.8% on NQ with Layer 3 enabled, and drives poisoned-document MRR to 0.000, while restoring clean accuracy from 13-33% under attack to 58-76%. Under an architecture-aware adversary who paraphrases triggers to evade the structural filter, enabling the consistency layer halves adaptive ASR (32.0% to 15.0% on NQ) while raising clean accuracy by 18 points, at an added latency of ~16-19 s/query under live retrieval.
Muhaimin Bin Munir, Akib Jawad Ononto, Nazia Shehnaz Joynab et al.· 0 citations
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 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.
Jiamin Chen, Yisen Gao, Yanping Li et al.· 0 citations
An Evaluation Agent, middleware that combines Natural Language Inference factual verification, a five-signal poison detector with relevance-weighted aggregation, and a Trust Index is proposed, which reliably blocks instruction injection of unsafe advice while contradiction and subtle semantic weakening remain hard.
Balkrishna Giri, M. Hasan, Jussi Rasku et al.· 0 citations
Persistent agent memory must adapt as later outcomes change earlier evidence, yet mutable retrieval weights create an attribution problem: reviewers must distinguish authorized adaptation from database tampering. We present MutMem, an authorized-mutation protocol in HOM-AIMOS, a persistent agent-memory engine. MutMem retains memory content, records signed positive and negative outcome evidence without age-based expiry, and commits each nontrivial weight change as a housekeeper-authorized transition. Each transition binds a terminal provenance node, signer epoch, quantized old and new weights, a no-fork predecessor, and two domain-separated SHA-256 commitments. Ed25519 verification runs in both the database writer and a portable verifier. Content classified as poison-likely is retained with signed, revisable labels used by recall as trust evidence. We evaluate utility, mutation integrity, and poisoning adaptation. HOM-AIMOS answers 459/500 LongMemEval questions correctly under LLM judgment (91.8%). On LoCoMo, it obtains 74.12% judged accuracy and, under a separate upstream-compatible protocol, 58.20 token F1. A native suite passes all declared authorization, topology, tamper, signer-epoch, and post-mutation-recall cases; median signed-transition latency is 4.865 ms. In a declared N=100 PoisonedRAG adaptation, no injected poison appears in attacked top-5 disclosures (0/100; 95% Wilson upper bound 3.70%), while induced target-answer attack success among 98 clean-negative targets is 1/98 (1.02%). A preregistered four-arm ablation attributes the retrieval reduction to signed stored labels: the retriever selects poison for 94/100 targets when epistemic policy is bypassed and 0/100 when labels are restored. MutMem provides evidence of integrity, authorization, traceability, and historical continuity; it does not establish content truth.
Walid Saidi· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
