English
Related papers

Related papers: The downgrading semantics of memory safety (Extend…

200 papers

External memory is a key component of modern large language model (LLM) systems, enabling long-term interaction and personalization. Despite its importance, memory management is still largely driven by hand-designed heuristics, offering…

Computation and Language · Computer Science 2025-12-29 Changzhi Sun , Xiangyu Chen , Jixiang Luo , Dell Zhang , Xuelong Li

Information-flow control systems often enforce progress-insensitive noninterference, as it is simple to understand and enforce. Unfortunately, real programs need to declassify results and endorse inputs, which noninterference disallows,…

Cryptography and Security · Computer Science 2025-07-29 Ethan Cecchetti

The ability to dynamically allocate memory is fundamental in modern programming languages. However, this feature is not adequately supported in current general-purpose PIM devices. To identify key design principles that PIM must consider,…

Hardware Architecture · Computer Science 2026-01-28 Dongjae Lee , Bongjoon Hyun , Youngjin Kwon , Minsoo Rhu

Semantic memory is the subsystem of human memory that stores knowledge of concepts or meanings, as opposed to life specific experiences. The organization of concepts within semantic memory can be understood as a semantic network, where the…

Online reinforcement learning agents are currently able to process an increasing amount of data by converting it into a higher order value functions. This expansion of the information collected from the environment increases the agent's…

Machine Learning · Computer Science 2021-02-04 Mirza Ramicic , Andrea Bonarini

We describe Elevator, a unifying polymorphic foundation for metaprogramming with memory management based on adjoint modalities. In this setting, we distinguish between multiple memory regions using modes where each mode has a specific set…

Programming Languages · Computer Science 2024-11-04 Junyoung Jang , Brigitte Pientka

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

Machine Learning · Computer Science 2025-11-14 James Jin Kang , Dang Bui , Thanh Pham , Huo-Chong Ling

Self-supervised learning is the backbone of state of the art language modeling. It has been argued that training with predictive loss on a self-supervised dataset causes simulators: entities that internally represent possible configurations…

Machine Learning · Computer Science 2024-01-31 Luke Marks

Memory poisoning attacks for Agentic AI and multi-agent systems (MAS) have recently caught attention. It is partially due to the fact that Large Language Models (LLMs) facilitate the construction and deployment of agents. Different memory…

Cryptography and Security · Computer Science 2026-03-24 Vicenç Torra , Maria Bras-Amorós

For the last thirty years, a large variety of memory allocators have been proposed. Since performance, memory usage and energy consumption of each memory allocator differs, software engineers often face difficult choices in selecting the…

Operating Systems · Computer Science 2024-06-25 José L. Risco-Martín , J. Manuel Colmenar , David Atienza , J. Ignacio Hidalgo

Obfuscation of computer programs has historically been approached either as a practical but \textit{ad hoc} craft to make reverse engineering subjectively difficult, or as a sound theoretical investigation unfortunately detached from the…

Cryptography and Security · Computer Science 2024-11-11 Ali Ajorian , Erick Lavoie , Christian Tschudin

We estimate the security of dictionary-based PINs (Personal Identification Numbers) that a user selects from his/her memory without any additional aids. The estimates take into account the distribution of words in source language. We use…

Cryptography and Security · Computer Science 2014-04-08 Martin Stanek

Memory reclamation for lock-based data structures is typically easy. However, it is a significant challenge for lock-free data structures. Automatic techniques such as garbage collection are inefficient or use locks, and non-automatic…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-12-05 Trevor Brown

This paper proposes a novel framework for developing safe Artificial General Intelligence (AGI) by combining Active Inference principles with Large Language Models (LLMs). We argue that traditional approaches to AI safety, focused on…

Artificial Intelligence · Computer Science 2025-08-11 Bo Wen

Iterators are a fundamental programming abstraction for traversing and modifying elements in containers in mainstream imperative languages such as C++. Iterators provide a uniform access mechanism that hides low-level implementation details…

Programming Languages · Computer Science 2026-04-16 Yihe Li , Gregory J. Duck

High capacity and scalable memory systems play a vital role in enabling our desktops, smartphones, and pervasive technologies like Internet of Things (IoT). Unfortunately, memory systems are becoming increasingly prone to faults. This is…

Hardware Architecture · Computer Science 2019-09-04 Prashant J. Nair

For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--inspired by human cognitive processes (hippocampal indexing/consolidation theory and…

Artificial Intelligence · Computer Science 2026-04-24 Yingjie Gu , Wenjian Xiong , Liqiang Wang , Pengcheng Ren , Chao Li , Xiaojing Zhang , Yijuan Guo , Qi Sun , Jingyao Ma , Shidang Shi

Safety policies define what constitutes safe and unsafe AI outputs, guiding data annotation and model development. However, annotation disagreement is pervasive and can stem from multiple sources such as operational failures (annotators…

Artificial Intelligence · Computer Science 2026-05-08 Alex Oesterling , Donghao Ren , Yannick Assogba , Dominik Moritz , Sunnie S. Y. Kim , Leon Gatys , Fred Hohman

Reinforcement Learning (RL) agents typically learn memoryless policies---policies that only consider the last observation when selecting actions. Learning memoryless policies is efficient and optimal in fully observable environments.…

Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments. However, this reliance on memory introduces a critical security risk: an adversary can…

Cryptography and Security · Computer Science 2025-10-06 Qianshan Wei , Tengchao Yang , Yaochen Wang , Xinfeng Li , Lijun Li , Zhenfei Yin , Yi Zhan , Thorsten Holz , Zhiqiang Lin , XiaoFeng Wang