The DOI matches its Crossref record; 9 of the 15 references it cites were found in a registry or an index, and 1 are not checked yet.
PROMPT PERSISTENCE ATTACKS: LONG-TERM MEMORY POISONING IN LLM-BASED SYSTEMS
Open accessAbstract
Large Language Models (LLMs) are increasingly deployed as persistent, interactive systems that retain information across user interactions. These memory mechanisms are designed to enhance personalization, task continuity, and operational efficiency. However, persistence introduces a new and insufficiently examined security risk: the gradual corruption of long-term memory through legitimate interaction. This paper introduces the concept of Prompt Persistence Attacks, a class of long-horizon adversarial strategies that exploit memory retention in deployed LLMbased systems. Unlike prompt injection or jailbreak attacks that aim to induce immediate policy violations, prompt persistence attacks operate incrementally, shaping system memory over time in ways that remain below conventional detection thresholds. We analyze how contemporary memory architectures used in real-world LLM deployments can be manipulated without violating explicit safety constraints. Through detailed threat modeling and scenario-based analysis, we demonstrate how poisoned memory can bias future reasoning, distort decisionmaking, and undermine alignment guarantees. The paper concludes by outlining the limitations of existing defenses and identifying key research challenges in securing memory-enabled AI systems.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Evaluating Large Language Models Trained on Code
Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. D. O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.03374 · Cited by 1,436
The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
Brundage, M., Avin, S., Clark, J., Toner, H., Eckersley, P., Garfinkel, B., Dafoe, A., Scharre, P., Zeitzoff, T., Filar, B., et al. (2018) · arXiv · doi:10.48550/arxiv.1802.07228 · Cited by 849
Red Teaming Language Models with Language Models
Perez, E., Huang, S., Song, F., Cai, T., Ring, R., Aslanides, J., Glaese, A., McAleese, N., & Irving, G. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.225 · Cited by 363
Universal and Transferable Adversarial Attacks on Aligned Language Models
Zou, A., Wang, Z., Carlini, N., Nasr, M., Kolter, J. Z., & Fredrikson, M. (2023) · arXiv · doi:10.48550/arxiv.2307.15043 · Cited by 197
Extracting Training Data from Diffusion Models
Carlini, N., Hayes, J., Nasr, M., Jagielski, M., Sehwag, V., Tramèr, F., Balle, B., Ippolito, D., & Wallace, E. (2023) · arXiv · doi:10.48550/arxiv.2301.13188
Untitled work
Openai (2023)
UnresolvedUntitled work
Anthropic (2023) · Constitutional AI: Harmlessness from AI Feedback
UnresolvedUntitled work
Kroll, J. A. (2017)
UnresolvedUntitled work
Floridi, L. (2018) · AI4People-An Ethical Framework for a Good
UnresolvedUntitled work
Nist (2023) · AI Risk Management Framework (AI RMF 1.0)
UnresolvedUntitled work
(2019) · Ethics Guidelines for Trustworthy AI
Unresolved
Metadata
- Authors
- Bhatnagar, P.
- Corresponding author
- Bhatnagar, Pranav
- ORCID
- Bhatnagar, Pranav
- Venue
- SSRN (preprint)
- Publisher
- Elsevier BV
- Published
- 2026
- ISSN
- 1556-5068 (ISSN-L)
- OpenAlex
- W7127941464
- Cited by
- 0
- References
- 15
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Locations
- SSRN Electronic Journal (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Hardware and Architecture › Security and Verification in Computing
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Keywords
- large language models, memory retention, adversarial attacks, AI alignment, threat modeling
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.