Related papers: SuperLocalMemory: Privacy-Preserving Multi-Agent M…

As artificial intelligence (AI) assistants become more widely adopted in safety-critical domains, it becomes important to develop safeguards against potential failures or adversarial attacks. A key prerequisite to developing these…

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,…

Multi-agent systems (MAS) powered by LLMs promise adaptive, reasoning-driven enterprise workflows, yet granting agents autonomous control over tools, memory, and communication introduces attack surfaces absent from deterministic pipelines.…

Persistent memory is a central capability for AI agents, yet the mathematical foundations of memory retrieval, lifecycle management, and consistency remain unexplored. Current systems employ cosine similarity for retrieval, heuristic decay…

AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips past every session-bound detector because only the aggregate carries the payload. We make…

Large language model agents equipped with persistent memory are vulnerable to memory poisoning attacks, where adversaries inject malicious instructions through query only interactions that corrupt the agents long term memory and influence…

Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously unrecognized threat to robust machine learning…

With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety…

Machine learning (ML) underpins foundation models in finance, healthcare, and critical infrastructure, making them targets for data poisoning, model extraction, prompt injection, automated jailbreaking, and preference-guided black-box…

The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to…

Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumption, the \emph{Misattribution Gap}, where memory-layer attacks produce behaviors…

Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although ''local offline fine-tuning'' is often viewed as a privacy boundary, we reveal that compromised model…

Indirect prompt injection threatens LLM agents by embedding malicious instructions in external content, enabling unauthorized actions and data theft. LLM agents maintain working memory through their context window, which stores interaction…

Memory plays a foundational role in augmenting the reasoning, adaptability, and contextual fidelity of modern Large Language Models and Multi-Modal LLMs. As these models transition from static predictors to interactive systems capable of…

Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…

Large language models (LLMs) frequently memorize sensitive information during training, posing risks when deploying publicly accessible models. Current machine unlearning methods struggle to selectively remove specific data associations…

Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents. Recent work has further explored augmenting these agents with memory mechanisms to support long-horizon reasoning.…

Persistent external memory enables LLM agents to maintain context across sessions, yet its security properties remain formally uncharacterized. We formalize memory poisoning attacks on retrieval-augmented agents as a Stackelberg game with a…

Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to…

Machine learning models have been widely adopted in several fields. However, most recent studies have shown several vulnerabilities from attacks with a potential to jeopardize the integrity of the model, presenting a new window of research…