Related papers: ADMIT: Few-shot Knowledge Poisoning Attacks on RAG…

Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of…

Similar to other machine learning frameworks, Offline Reinforcement Learning (RL) is shown to be vulnerable to poisoning attacks, due to its reliance on externally sourced datasets, a vulnerability that is exacerbated by its sequential…

Retrieval-Augmented Generation (RAG) enhances Large Language Models by grounding their outputs in external documents. These systems, however, remain vulnerable to attacks on the retrieval corpus, such as prompt injection. RAG-based search…

Large language models (LLMs) frequently hallucinate, limiting their reliability in knowledge-intensive applications. Retrieval-augmented generation (RAG) and conformal factuality have emerged as potential ways to address this limitation.…

We consider availability data poisoning attacks, where an adversary aims to degrade the overall test accuracy of a machine learning model by crafting small perturbations to its training data. Existing poisoning strategies can achieve the…

Neural Ranking Models (NRMs) are central to modern information retrieval but remain highly vulnerable to adversarial manipulation. Existing attacks often rely on heuristics or surrogate models, limiting effectiveness and transferability. We…

With the rapid development of the Vision-Language Model (VLM), significant progress has been made in Visual Question Answering (VQA) tasks. However, existing VLM often generate inaccurate answers due to a lack of up-to-date knowledge. To…

Short answer assessment is a vital component of science education, allowing evaluation of students' complex three-dimensional understanding. Large language models (LLMs) that possess human-like ability in linguistic tasks are increasingly…

Successful defense against dynamically evolving cyber threats requires advanced and sophisticated techniques. This research presents a novel approach to enhance real-time cybersecurity threat detection and response by integrating large…

Large language models (LLMs) augmented with retrieval systems have demonstrated significant potential in handling knowledge-intensive tasks. However, these models often struggle with unfaithfulness issues, generating outputs that either…

Recommender systems play a crucial role in helping users to find their interested information in various web services such as Amazon, YouTube, and Google News. Various recommender systems, ranging from neighborhood-based,…

The widespread adoption of generative models such as Stable Diffusion and ChatGPT has made them increasingly attractive targets for malicious exploitation, particularly through data poisoning. Existing poisoning attacks compromising…

Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs). However, standard RAG pipelines often fail to ensure that model reasoning remains consistent with the…

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Role-playing Large language models (LLMs) are increasingly deployed in high-stakes domains such as healthcare, education, and governance, where failures can directly impact user trust and well-being. A cost effective paradigm for LLM…

Federated learning is highly susceptible to model poisoning attacks, especially those meticulously crafted for servers. Traditional defense methods mainly focus on updating assessments or robust aggregation against manually crafted myopic…

Retrieval-Augmented Generation (RAG) significantly improves the factuality of Large Language Models (LLMs), yet standard pipelines often lack mechanisms to verify inter- mediate reasoning, leaving them vulnerable to hallucinations in…

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in…

Retrieval-Augmented Generation (RAG) has become a foundational paradigm for equipping large language models (LLMs) with external knowledge, playing a critical role in information retrieval and knowledge-intensive applications. However,…

Large language model (LLM) agents are increasingly employing retrieval-augmented generation (RAG) to improve the factuality of their responses. However, in practice, these systems often need to handle ambiguous user queries and potentially…