Related papers: Mind the Web: The Security of Web Use Agents
Large Language Model (LLM) agents remain vulnerable to safety threats from the external environment, where attackers inject adversarial content into external observations such as tool-returned data, webpages, or MCP context, causing harmful…
Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration into reusable workflows. This makes skills useful, but it also…
The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…
Large language models (LLMs) have demonstrated impressive results on natural language tasks, and security researchers are beginning to employ them in both offensive and defensive systems. In cyber-security, there have been multiple research…
LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinformation in an online forum or selling illicit substances on…
Graphical user interface (GUI) agents built on multimodal large language models (MLLMs) have recently demonstrated strong decision-making abilities in screen-based interaction tasks. However, they remain highly vulnerable to pop-up-based…
With the proliferation of LLM-driven multi-agent systems (MAS), the security of Web links has become a critical concern. Once MAS is induced to trust a malicious link, attackers can use it as a springboard to expand the attack surface. In…
As LLMs are increasingly integrated into systems that browse, retrieve, summarize, and act on web content, webpages have become an untrusted input vector for downstream model behavior. This enables site owners, contributors, and adversaries…
Large Language Model (LLM) agents are rapidly improving to handle increasingly complex web-based tasks. Most of these agents rely on general-purpose, proprietary models like GPT-4 and focus on designing better prompts to improve their…
Large Vision-Language Models (LVLMs) empower autonomous mobile agents, yet their security under realistic mobile deployment constraints remains underexplored. While agents are vulnerable to visual prompt injections, stealthily executing…
Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex…
Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious instructions into webpage content to induce unintended…
Recent advances in browser-based LLM agents have shown promise for automating tasks ranging from simple form filling to hotel booking or online shopping. Current benchmarks measure agent performance in controlled environments, such as…
Large Language Model (LLM) web agents often struggle with long-horizon web navigation and web task completion in new websites, producing inefficient action sequences unless fine-tuned on environment-specific data. We show that…
LLM agents have demonstrated remarkable performance across various applications, primarily due to their advanced capabilities in reasoning, utilizing external knowledge and tools, calling APIs, and executing actions to interact with…
Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely…
Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…
Autonomous agents powered by Large Language Models (LLMs) acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for…
Jailbreak attacks on Language Model Models (LLMs) entail crafting prompts aimed at exploiting the models to generate malicious content. Existing jailbreak attacks can successfully deceive the LLMs, however they cannot deceive the human.…
As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions,…