Related papers: SuperLocalMemory: Privacy-Preserving Multi-Agent M…
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…
Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research…
Large Language Model (LLM) agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or…
Large language model (LLM)-powered agents are increasingly used in recommender systems (RSs) to achieve personalized behavior modeling, where the memory mechanism plays a pivotal role in enabling the agents to autonomously explore, learn…
Federated learning (FL) enables collaborative model training while preserving data privacy, but its decentralized nature exposes it to client-side data poisoning attacks (DPAs) and model poisoning attacks (MPAs) that degrade global model…
The advent of continuously learning Artificial Intelligence (AI) assistants marks a paradigm shift from episodic interactions to persistent, memory-driven relationships. This paper introduces the concept of "Cognitive Sovereignty", the…
Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on…
Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to full retraining, this work reveals that they fail to…
Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models (LLMs), Vision-Language Models (VLMs), and new agentic AI systems, like LangChain and…
Large language model (LLM) agents increasingly leverage long term memory to support persistent and autonomous task execution. However, this capability also introduces a new attack surface: memory poisoning, where adversaries can inject…
In the evolving landscape of Federated Learning (FL), a new type of attacks concerns the research community, namely Data Poisoning Attacks, which threaten the model integrity by maliciously altering training data. This paper introduces a…
This article surveys Cognitive Edge Computing as a practical and methodical pathway for deploying reasoning-capable Large Language Models (LLMs) and autonomous AI agents on resource-constrained devices at the network edge. We present a…
This position paper aims to rethink the role and design of memory in Large Language Model (LLM)-based agent systems. We observe that while current memory practices have begun to transcend the limitations of single interactions, they remain…
As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy…
The growing reliance on artificial intelligence (AI) in customer support has significantly improved operational efficiency and user experience. However, traditional machine learning (ML) approaches, which require extensive local training on…
Post-mortem analysis of compromised systems is a key aspect of cyber forensics, today a mostly manual, slow, and error-prone task. Agentic AI, i.e., LLM-powered agents, is a promising avenue for automation. However, applying such agents to…
As generative agents become increasingly sophisticated and deployed in long-term interactive scenarios, their memory management capabilities emerge as a critical bottleneck for both performance and privacy. Current approaches either…
We propose a novel clustering mechanism based on an incompatibility property between subsets of data that emerges during model training. This mechanism partitions the dataset into subsets that generalize only to themselves, i.e., training…
Recent advances in AI are transforming AI's ubiquitous presence in our world from that of standalone AI-applications into deeply integrated AI-agents. These changes have been driven by agents' increasing capability to autonomously make…
Research in adversarial machine learning (AML) has shown that statistical models are vulnerable to maliciously altered data. However, despite advances in Bayesian machine learning models, most AML research remains concentrated on classical…