相关论文: DeRAG: Black-box Adversarial Attacks on Multiple R…

The growing adoption of Retrieval-Augmented Generation (RAG) has led to a rise in adversarial attacks. Existing defenses, relying on semantic analysis or voting, face a trade-off between high computational cost and limited robustness under…

Retrieval-Augmented Generation (RAG) has become a robust framework for enhancing Large Language Models (LLMs) with external knowledge. Recent advances in RAG have investigated graph based retrieval for intricate reasoning; however, the…

Retrieval-Augmented Generation (RAG) has greatly improved large language models (LLMs) by enabling them to generate accurate, contextually grounded responses through the integration of external information. However, conventional RAG…

Large Language Models (LLMs) have demonstrated remarkable capabilities in generating coherent text but remain limited by the static nature of their training data. Retrieval Augmented Generation (RAG) addresses this issue by combining LLMs…

Retrieval-Augmented Generation (RAG) is widely used to augment large language models with external knowledge retrieval to improve reliability and generalization. However, recent studies have shown that RAG systems remain vulnerable to data…

Retrieval augmented generation (RAG) reduces hallucinations and factual errors in large language models (LLMs) by conditioning generation on retrieved external knowledge. Recent search agents further cast RAG as an autonomous, multi-turn…

Current LLM alignment methods are readily broken through specifically crafted adversarial prompts. While crafting adversarial prompts using discrete optimization is highly effective, such attacks typically use more than 100,000 LLM calls.…

Retrieval-augmented Generation (RAG) is a prevalent approach for domain-specific LLMs, yet it is often plagued by "Retrieval Hallucinations"--a phenomenon where fine-tuned models fail to recognize and act upon poor-quality retrieved…

Retrieval-augmented generation (RAG) systems respond to queries by retrieving relevant documents from a knowledge database and applying an LLM to the retrieved documents. We demonstrate that RAG systems that operate on databases with…

Gradient optimization-based adversarial attack methods automate the learning of adversarial triggers to generate jailbreak prompts or leak system prompts. In this work, we take a closer look at the optimization objective of adversarial…

Prompt injection attacks pose a significant challenge to the safe deployment of Large Language Models (LLMs) in real-world applications. While prompt-based detection offers a lightweight and interpretable defense strategy, its effectiveness…

Retrieval-Augmented Generation (RAG) integrates Large Language Models (LLMs) with external knowledge bases, improving output quality while introducing new security risks. Existing studies on RAG vulnerabilities typically focus on exploiting…

Retrieval-Augmented Generation (RAG) significantly mitigates the hallucinations and domain knowledge deficiency in large language models by incorporating external knowledge bases. However, the multi-module architecture of RAG introduces…

Crafting effective reward signals remains a central challenge in Reinforcement Learning (RL), especially for complex reasoning tasks. Existing automated reward optimization methods typically rely on derivative-free search heuristics that…

Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address the impracticality of existing white-box/gray-box methods and…

Retrieval-Augmented Generation (RAG) increases the reliability and trustworthiness of the LLM response and reduces hallucination by eliminating the need for model retraining. It does so by adding external data into the LLM's context. We…

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications, e.g., medical question-answering, mathematical sciences, and code generation. However, they also exhibit inherent limitations, such…

Prompting interfaces allow users to quickly adjust the output of generative models in both vision and language. However, small changes and design choices in the prompt can lead to significant differences in the output. In this work, we…

The application of deep recurrent networks to audio transcription has led to impressive gains in automatic speech recognition (ASR) systems. Many have demonstrated that small adversarial perturbations can fool deep neural networks into…

Retrieval-augmented generation (RAG) enhances factual grounding by integrating retrieval mechanisms with generative models but introduces new attack surfaces, particularly through backdoor attacks. While prior research has largely focused…