Related papers: Deep-Research Agents Can Be Poisoned via User-Gene…
According to recent empirical studies, a majority of users have the same, or very similar, passwords across multiple password-secured online services. This practice can have disastrous consequences, as one password being compromised puts…
Developers spend much time finding information that is relevant to their questions. Stack Overflow has been the leading resource, and with the advent of Large Language Models (LLMs), generative models such as ChatGPT are used frequently.…
The dissemination of Large Language Models (LLMs), trained at scale, and endowed with powerful text-generating abilities, has made it easier for all to produce harmful, toxic, faked or forged content. In response, various proposals have…
Deepfake videos are defined as a resulting media from the synthesis of different persons images and videos, mostly faces, replacing a real one. The easy spread of such videos leads to elevated misinformation and represents a threat to…
As large language models (LLMs) become more specialized, we envision a future where millions of expert LLMs exist, each trained on proprietary data and excelling in specific domains. In such a system, answering a query requires selecting a…
Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs…
Large language models are increasingly augmented with persistent memory, allowing assistants to store user-specific information across sessions for personalization and continuity. This statefulness introduces a new security risk:…
Dense retrievers have achieved state-of-the-art performance in various information retrieval tasks, but to what extent can they be safely deployed in real-world applications? In this work, we propose a novel attack for dense retrieval…
Participation on social media platforms has many benefits but also poses substantial threats. Users often face an unintended loss of privacy, are bombarded with mis-/disinformation, or are trapped in filter bubbles due to over-personalized…
Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We…
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding responses with retrieved information. As an emerging paradigm, Agentic RAG further enhances this process by introducing autonomous LLM agents into the…
While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can…
Major search engine providers are rapidly incorporating Large Language Model (LLM)-generated content in response to user queries. These conversational search engines operate by loading retrieved website text into the LLM context for…
Agentic search has emerged as a promising paradigm for complex information seeking by enabling Large Language Models (LLMs) to interleave reasoning with tool use. However, prevailing systems rely on monolithic agents that suffer from…
We aim to develop a multimodal research agent capable of explicit reasoning and planning, multi-tool invocation, and cross-modal information synthesis, enabling it to conduct deep research tasks. However, we observe three main challenges in…
Recent work in open-domain question answering (ODQA) has shown that adversarial poisoning of the search collection can cause large drops in accuracy for production systems. However, little to no work has proposed methods to defend against…
Search engines are crucial as they provide an efficient and easy way to access vast amounts of information on the internet for diverse information needs. User queries, even with a specific need, can differ significantly. Prior research has…
Deep search agents, which autonomously iterate through multi-turn web-based reasoning, represent a promising paradigm for complex information-seeking tasks. However, current agents suffer from critical inefficiency: they conduct excessive…
Recent studies have shown that recommender systems (RSs) are highly vulnerable to data poisoning attacks, where malicious actors inject fake user profiles, including a group of well-designed fake ratings, to manipulate recommendations. Due…
Retrieval-Augmented Generation (RAG) systems typically treat documents as flat text, ignoring the structured metadata and linked relationships that knowledge graphs provide. In this paper, we investigate whether structured linked data,…