Related papers: AgentSys: Secure and Dynamic LLM Agents Through Ex…

Web-use agents are rapidly being deployed to automate complex web tasks with extensive browser capabilities. However, these capabilities create a critical and previously unexplored attack surface. This paper demonstrates how attackers can…

Large Language Model (LLM) agents are increasingly integrated into critical systems, leveraging external tools to interact with the real world. However, this capability exposes them to Indirect Prompt Injection (IPI), where attackers embed…

LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate the LLM's intended behavior. Recent defenses based on…

Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong…

Large language models (LLMs) based recommender systems (RecSys) can adapt to different domains flexibly. It utilizes in-context learning (ICL), i.e., prompts, to customize the recommendation functions, which include sensitive historical…

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…

Open-domain dialogue systems have seen remarkable advancements with the development of large language models (LLMs). Nonetheless, most existing dialogue systems predominantly focus on brief single-session interactions, neglecting the…

Enterprise AI deploys dozens of autonomous agent nodes across workflows, each acting on the same entities with no shared memory and no common governance. We identify five structural challenges arising from this memory governance gap: memory…

Complex tasks are increasingly delegated to ensembles of specialized LLM-based agents that reason, communicate, and coordinate actions-both among themselves and through interactions with external tools, APIs, and databases. While persistent…

We present NeuSymMS, an adaptive memory system that enables large language model (LLM) agents to learn, remember, and reason about users across sessions via a hybrid neuro-symbolic architecture. NeuSymMS couples neural fact extraction from…

Large language model (LLM) agents have evolved to intelligently process information, make decisions, and interact with users or tools. A key capability is the integration of long-term memory capabilities, enabling these agents to draw upon…

As large language models (LLMs) become integrated into various sensitive applications, prompt injection, the use of prompting to induce harmful behaviors from LLMs, poses an ever increasing risk. Prompt injection attacks can cause LLMs to…

Large language models (LLMs) remain vulnerable to jailbreak prompts that elicit harmful or policy-violating outputs, while many existing defenses rely on expensive fine-tuning, intrusive prompt rewriting, or external guardrails that add…

Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit when under attack. In this paper, we evaluate the robustness of LLM-based agentic systems against…

Large Language Model-based systems (LLM systems) are information and query processing systems that use LLMs to plan operations from natural-language prompts and feed the output of each successive step into the LLM to plan the next. This…

LLM Agents are becoming central to intelligent systems. However, their deployment raises serious safety concerns. Existing defenses largely rely on "Safety Checks", which struggle to capture the complex semantic risks posed by harmful user…

The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the…

As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn,…

Large Language Model (LLM) agent systems have experienced rapid adoption across diverse domains, yet they suffer from critical user experience problems that limit their practical deployment. Through an empirical analysis of over 40,000…

Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an external environment; this makes them susceptible to prompt injections when dealing with untrusted data. To overcome this limitation, we propose…