Related papers: Deep-Research Agents Can Be Poisoned via User-Gene…

The proliferation of Large Language Model (LLM)-based Graphical User Interface (GUI) agents in web browsing scenarios present complex unintended consequences (UCs). This paper characterizes three UCs from three perspectives: phenomena,…

Large Language Models (LLMs) have enabled agents to move beyond conversation toward end-to-end task execution and become more helpful. However, this helpfulness introduces new security risks stem less from direct interface abuse than from…

Prompt injection attacks represent a major vulnerability in Large Language Model (LLM) deployments, where malicious instructions embedded in user inputs can override system prompts and induce unintended behaviors. This paper presents a…

Generative deep learning models are able to create realistic audio and video. This technology has been used to impersonate the faces and voices of individuals. These ``deepfakes'' are being used to spread misinformation, enable scams,…

Data contamination refers to the leakage of evaluation data into model training data, resulting in overfitting to supposedly held-out test sets and compromising test validity. We identify an analogous issue, search-time contamination (STC),…

Deep research has emerged as a transformative capability for autonomous agents, empowering Large Language Models to navigate complex, open-ended tasks. However, realizing its full potential is hindered by critical limitations, including…

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

Complex systems have interested researchers across a broad range of fields for many years and as computing has become more accesible and feasible, it is now possible to simulate aspects of these systems. A major point of research is how…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating up-to-date external knowledge, yet real-world web environments present unique challenges. These limitations manifest as two key challenges: pervasive…

Large language models (LLMs) integrated with retrieval-augmented generation (RAG) systems improve accuracy by leveraging external knowledge sources. However, recent research has revealed RAG's susceptibility to poisoning attacks, where the…

Agentic AI and Multi-Agent Systems are poised to dominate industry and society imminently. Powered by goal-driven autonomy, they represent a powerful form of generative AI, marking a transition from reactive content generation into…

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…

Major search engines deploy personalized Web results to enhance users' experience, by showing them data supposed to be relevant to their interests. Even if this process may bring benefits to users while browsing, it also raises concerns on…

Tool-use large language model (LLM) agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external API access, and session memory management. While prior research has examined various threats,…

This work addresses challenges related to attacks on social tagging systems, which often comes in a form of malicious annotations or profile injection attacks. In particular, we study various countermeasures against two types of threats for…

Malicious crowdsourcing forums are gaining traction as sources of spreading misinformation online, but are limited by the costs of hiring and managing human workers. In this paper, we identify a new class of attacks that leverage deep…

Recently, people have suffered from LLM hallucination and have become increasingly aware of the reliability gap of LLMs in open and knowledge-intensive tasks. As a result, they have increasingly turned to search-augmented LLMs to mitigate…

The rapid proliferation of misinformation in digital media demands solutions that go beyond isolated Large Language Model(LLM) or AI Agent based detection methods. This paper introduces a novel multi-agent framework that covers the complete…

Automatically extracting effective queries is challenging in information retrieval, especially in toxic content exploration, as such content is likely to be disguised. With the recent achievements in generative Large Language Model (LLM),…

Deep Research Agents (DRAs) aim to solve complex, long-horizon research tasks involving planning, retrieval, multimodal understanding, and report generation, yet their evaluation remains challenging due to dynamic web environments and…