相关论文: Smoothed Embeddings for Robust Language Models

The rapid adoption of large language models (LLMs) has brought both transformative applications and new security risks, including jailbreak attacks that bypass alignment safeguards to elicit harmful outputs. Existing automated jailbreak…

Large Language Models (LLMs) exhibit strong but shallow alignment: they directly refuse harmful queries when a refusal is expected at the very start of an assistant turn, yet this protection collapses once a harmful continuation is underway…

The widespread use of large language models (LLMs) is increasing the demand for methods that detect machine-generated text to prevent misuse. The goal of our study is to stress test the detectors' robustness to malicious attacks under…

With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…

Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs). However, the effectiveness of existing approaches degrades in massive editing scenarios, particularly when evaluated with practical…

Text embeddings from large language models (LLMs) have achieved excellent results in tasks such as information retrieval, semantic textual similarity, etc. In this work, we show an interesting finding: when feeding a text into the LLM-based…

Large Language Models (LLMs) have gained enormous attention in recent years due to their capability of understanding and generating natural languages. With the rapid development and wild-range applications (e.g., Agents, Embodied…

Despite recent monumental advances in the field, many Natural Language Processing (NLP) models still struggle to perform adequately on noisy domains. We propose a novel probabilistic embedding-level method to improve the robustness of NLP…

Stochastic embedding transitions introduce a probabilistic mechanism for adjusting token representations dynamically during inference, mitigating the constraints imposed through static or deterministic embeddings. A transition framework was…

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

Recent developments in Large Language Models (LLMs) have manifested significant advancements. To facilitate safeguards against malicious exploitation, a body of research has concentrated on aligning LLMs with human preferences and…

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

This article introduces a novel and fast method for refining pre-trained static word or, more generally, token embeddings. By incorporating the embeddings of neighboring tokens in text corpora, it continuously updates the representation of…

Large language models (LLMs) have achieved impressive capabilities, yet ensuring their safety against harmful prompts remains a critical challenge. Recent work has revealed that the latent representations (embeddings) of harmful and safe…

The advancement of Large Language Models (LLMs) has led to increasing concerns about the misuse of AI-generated text, and watermarking for LLM-generated text has emerged as a potential solution. However, it is challenging to generate…

Text clustering is an important method for organising the increasing volume of digital content, aiding in the structuring and discovery of hidden patterns in uncategorised data. The effectiveness of text clustering largely depends on the…

Large language models (LLMs) achieve impressive performance across diverse tasks yet remain vulnerable to jailbreak attacks that bypass safety mechanisms. We present RAID (Refusal-Aware and Integrated Decoding), a framework that…

Neural ranking models have achieved remarkable progress and are now widely deployed in real-world applications such as Retrieval-Augmented Generation (RAG). However, like other neural architectures, they remain vulnerable to adversarial…

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously unrecognized threat to robust machine learning…