English
Related papers

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

200 papers

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data. This phenomenon raises critical questions about model behavior, privacy risks,…

Machine Learning · Computer Science 2025-12-15 Alexander Xiong , Xuandong Zhao , Aneesh Pappu , Dawn Song

Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is crucial for robust safety mechanisms. Existing attacks primarily distract LLMs by introducing…

Computation and Language · Computer Science 2025-11-04 Peng Ding , Jun Kuang , Wen Sun , Zongyu Wang , Xuezhi Cao , Xunliang Cai , Jiajun Chen , Shujian Huang

LLMs are now an integral part of information retrieval. As such, their role as question answering chatbots raises significant concerns due to their shown vulnerability to adversarial man-in-the-middle (MitM) attacks. Here, we propose the…

Cryptography and Security · Computer Science 2026-03-25 Alina Fastowski , Bardh Prenkaj , Yuxiao Li , Gjergji Kasneci

Large language model (LLM) agents increasingly operate in settings where a single context window is far too small to capture what has happened, what was learned, and what should not be repeated. Memory -- the ability to persist, organize,…

Artificial Intelligence · Computer Science 2026-03-10 Pengfei Du

The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that…

Computation and Language · Computer Science 2025-03-18 Xuanli He , Jun Wang , Qiongkai Xu , Pasquale Minervini , Pontus Stenetorp , Benjamin I. P. Rubinstein , Trevor Cohn

Quantization leverages lower-precision weights to reduce the memory usage of large language models (LLMs) and is a key technique for enabling their deployment on commodity hardware. While LLM quantization's impact on utility has been…

Machine Learning · Computer Science 2024-11-05 Kazuki Egashira , Mark Vero , Robin Staab , Jingxuan He , Martin Vechev

Large Language Models (LLMs) are prone to memorizing training data, which poses serious privacy risks. Two of the most prominent concerns are training data extraction and Membership Inference Attacks (MIAs). Prior research has shown that…

Machine Learning · Computer Science 2026-03-02 Ali Al Sahili , Ali Chehab , Razane Tajeddine

We present SuperLocalMemory, a local-first memory system for multi-agent AI that defends against OWASP ASI06 memory poisoning through architectural isolation and Bayesian trust scoring, while personalizing retrieval through adaptive…

Artificial Intelligence · Computer Science 2026-03-04 Varun Pratap Bhardwaj

The increasing access to data poses both opportunities and risks in deep learning, as one can manipulate the behaviors of deep learning models with malicious training samples. Such attacks are known as data poisoning. Recent advances in…

Machine Learning · Computer Science 2023-06-29 Wenxiao Wang , Soheil Feizi

Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training datasets can be practically poisoned by malicious actors; and…

Cryptography and Security · Computer Science 2024-10-18 Yiming Zhang , Javier Rando , Ivan Evtimov , Jianfeng Chi , Eric Michael Smith , Nicholas Carlini , Florian Tramèr , Daphne Ippolito

The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This…

Cryptography and Security · Computer Science 2025-10-03 Niloofar Mireshghallah , Tianshi Li

Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks…

Artificial Intelligence · Computer Science 2024-03-11 Xiaogeng Liu , Zhiyuan Yu , Yizhe Zhang , Ning Zhang , Chaowei Xiao

Adversarial poisoning attacks pose huge threats to various machine learning applications. Especially, the recent accumulative poisoning attacks show that it is possible to achieve irreparable harm on models via a sequence of imperceptible…

Machine Learning · Computer Science 2023-06-07 Jianing Zhu , Xiawei Guo , Jiangchao Yao , Chao Du , Li He , Shuo Yuan , Tongliang Liu , Liang Wang , Bo Han

Small language models (SLMs) are increasingly valued for their efficiency and deployability in resource-constrained environments, making them useful for on-device, privacy-sensitive, and edge computing applications. On the other hand,…

Artificial Intelligence · Computer Science 2025-08-05 Roya Arkhmammadova , Hosein Madadi Tamar , M. Emre Gursoy

Similar to other machine learning frameworks, Offline Reinforcement Learning (RL) is shown to be vulnerable to poisoning attacks, due to its reliance on externally sourced datasets, a vulnerability that is exacerbated by its sequential…

Machine Learning · Computer Science 2025-05-28 Shijie Liu , Andrew C. Cullen , Paul Montague , Sarah Erfani , Benjamin I. P. Rubinstein

With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…

Machine Learning · Computer Science 2025-10-17 Fatmazohra Rezkellah , Ramzi Dakhmouche

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…

Cryptography and Security · Computer Science 2020-12-10 Liwei Song , Prateek Mittal

Large Language Models (LLMs) are increasingly employed as evaluators (LLM-as-a-Judge) for assessing the quality of machine-generated text. This paradigm offers scalability and cost-effectiveness compared to human annotation. However, the…

Computation and Language · Computer Science 2025-05-20 Narek Maloyan , Bislan Ashinov , Dmitry Namiot

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…

Machine Learning · Computer Science 2024-11-11 Andy Zhou , Bo Li , Haohan Wang

Indiscriminate data poisoning attacks aim to decrease a model's test accuracy by injecting a small amount of corrupted training data. Despite significant interest, existing attacks remain relatively ineffective against modern machine…

Machine Learning · Computer Science 2023-06-07 Yiwei Lu , Gautam Kamath , Yaoliang Yu