English
Related papers

Related papers: Memory Poisoning Attack and Defense on Memory Base…

200 papers

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

Cryptography and Security · Computer Science 2024-01-03 Daniel Wankit Yip , Aysan Esmradi , Chun Fai Chan

Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to mitigate LLM hallucinations and enhance their performance in knowledge-intensive domains. However, these systems are vulnerable to adversarial poisoning…

Information Retrieval · Computer Science 2025-07-29 Jinyan Su , Jin Peng Zhou , Zhengxin Zhang , Preslav Nakov , Claire Cardie

Memory plays a pivotal role in enabling large language model~(LLM)-based agents to engage in complex and long-term interactions, such as question answering (QA) and dialogue systems. While various memory modules have been proposed for these…

Computation and Language · Computer Science 2024-12-23 Ruihong Zeng , Jinyuan Fang , Siwei Liu , Zaiqiao Meng

Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On…

Machine Learning · Computer Science 2026-04-07 Aobo Chen , Chenxu Zhao , Chenglin Miao , Mengdi Huai

We introduce MemLineage, a defense for LLM agent memory that attaches both cryptographic provenance and LLM-mediated derivation lineage to every entry. Recent and concurrent work shows that untrusted content can be written into persistent…

Cryptography and Security · Computer Science 2026-05-15 Ciyan Ouyang , Rui Hou

Data poisoning considers cases when an adversary manipulates the behavior of machine learning algorithms through malicious training data. Existing threat models of data poisoning center around a single metric, the number of poisoned…

Machine Learning · Computer Science 2023-12-08 Wenxiao Wang , Soheil Feizi

Navigation agents powered by large language models (LLMs) convert natural language instructions into executable plans and actions. Compared to text-based applications, their security is far more critical: a successful prompt injection…

Cryptography and Security · Computer Science 2026-01-21 Jiani Liu , Yixin He , Lanlan Fan , Qidi Zhong , Yushi Cheng , Meng Zhang , Yanjiao Chen , Wenyuan Xu

Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…

Cryptography and Security · Computer Science 2025-06-09 Tingchen Fu , Mrinank Sharma , Philip Torr , Shay B. Cohen , David Krueger , Fazl Barez

This paper investigates some of the risks introduced by "LLM poisoning," the intentional or unintentional introduction of malicious or biased data during model training. We demonstrate how a seemingly improved LLM, fine-tuned on a limited…

Cryptography and Security · Computer Science 2025-11-05 Patrick Karlsen , Even Eilertsen

Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of…

Computer Vision and Pattern Recognition · Computer Science 2020-04-27 Loc Truong , Chace Jones , Brian Hutchinson , Andrew August , Brenda Praggastis , Robert Jasper , Nicole Nichols , Aaron Tuor

Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have shown improved performance in generating accurate responses. However, the dependence on external knowledge bases introduces potential security…

Cryptography and Security · Computer Science 2026-04-10 Zhiyuan Chang , Mingyang Li , Xiaojun Jia , Junjie Wang , Yuekai Huang , Ziyou Jiang , Yang Liu , Qing Wang

Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…

Cryptography and Security · Computer Science 2023-06-30 Nils Lukas , Florian Kerschbaum

Long-term memory has emerged as a foundational component of autonomous Large Language Model (LLM) agents, enabling continuous adaptation, lifelong multimodal learning, and sophisticated reasoning. However, as memory systems transition from…

Artificial Intelligence · Computer Science 2026-05-20 Chingkwun Lam , Jiaxin Li , Lingfei Zhang , Kuo Zhao

Data poisoning is a training-time attack that undermines the trustworthiness of learned models. In a targeted data poisoning attack, an adversary manipulates the training dataset to alter the classification of a targeted test point. Given…

Machine Learning · Computer Science 2025-11-18 Nakshatra Gupta , Sumanth Prabhu , Supratik Chakraborty , R Venkatesh

Memory-safety attacks have been one of the most critical threats against computing systems. Although a wide-range of defense techniques have been developed against these attacks, the existing mitigation strategies have several limitations.…

Cryptography and Security · Computer Science 2019-09-20 Eyasu Getahun Chekole , Unnikrishnan Cheramangalath , Sudipta Chattopadhyay , Martin Ochoa , Guo Huaqun

We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…

Machine Learning · Computer Science 2020-08-20 Amin Rakhsha , Goran Radanovic , Rati Devidze , Xiaojin Zhu , Adish Singla

Modern agentic systems allow Large Language Model (LLM) agents to tackle complex tasks through extensive tool usage, forming structured control flows of tool selection and execution. Existing security analyses often treat these control…

Cryptography and Security · Computer Science 2026-05-12 Zhenlin Xu , Xiaogang Zhu , Yu Yao , Minhui Xue , Yiliao Song

A popular class of defenses against prompt injection attacks on large language models (LLMs) relies on fine-tuning to separate instructions and data, so that the LLM does not follow instructions that might be present with data. We evaluate…

Cryptography and Security · Computer Science 2025-12-18 Nishit V. Pandya , Andrey Labunets , Sicun Gao , Earlence Fernandes

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

Cryptography and Security · Computer Science 2026-04-01 Chong Xiang , Drew Zagieboylo , Shaona Ghosh , Sanjay Kariyappa , Kai Greshake , Hanshen Xiao , Chaowei Xiao , G. Edward Suh

Retrieval-augmented generation (RAG) has become a common practice in multimodal large language models (MLLM) to enhance factual grounding and reduce hallucination. Yet, its reliance on retrieval exposes MLLMs to knowledge poisoning attacks,…

‹ Prev 1 3 4 5 6 7 10 Next ›