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