Related papers: When Alignment Isn't Enough: Response-Path Attacks…

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

As Large Language Model (LLM) agents increasingly gain self-evolutionary capabilities to adapt and refine their strategies through real-world interaction, their long-term reliability becomes a critical concern. We identify the Alignment…

Recently, Large Language Models (LLMs) have made significant advancements and are now widely used across various domains. Unfortunately, there has been a rising concern that LLMs can be misused to generate harmful or malicious content.…

Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to…

Retrieval-Augmented Generation (RAG) enhances the capabilities of large language models (LLMs) by incorporating external knowledge, but its reliance on potentially poisonable knowledge bases introduces new availability risks. Attackers can…

Language Model Agents (LMAs) are emerging as a powerful primitive for augmenting red-team operations. They can support attack planning, adversary emulation, and the orchestration of multi-step activity such as lateral movement, a core…

Large Language Model (LLM) agents are increasingly being deployed as conversational assistants capable of performing complex real-world tasks through tool integration. This enhanced ability to interact with external systems and process…

Modern LLM agents solve complex tasks by operating in iterative execution loops, where they repeatedly reason, act, and self-evaluate progress to determine when a task is complete. In this work, we show that while this self-directed loop…

Large Language Models (LLMs) exhibit strong but shallow alignment: they directly refuse harmful queries when a refusal is expected at the very start of an assistant turn, yet this protection collapses once a harmful continuation is underway…

Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting…

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting adversarial prompts. Predominant token-level optimization methods…

Large language models (LLMs) are susceptible to social-engineered attacks that are human-interpretable but require a high level of comprehension for LLMs to counteract. Existing defensive measures can only mitigate less than half of these…

As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns. This paper introduces Sequential Tool Attack Chaining (STAC), a novel…

Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability. However, when these…

AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication. While these advancements offer immense utility, they also inherit and amplify…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example,…

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…

Tool-Based Agent Systems (TBAS) allow Language Models (LMs) to use external tools for tasks beyond their standalone capabilities, such as searching websites, booking flights, or making financial transactions. However, these tools greatly…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…