相关论文: SECNEURON: Reliable and Flexible Abuse Control in …

Large language models (LLMs) and multimodal LLMs are typically safety-aligned before release to prevent harmful content generation. However, recent studies show that safety behaviors are concentrated in a small subset of parameters, making…

Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, current techniques fundamentally suffer from intertwined deficiencies: insufficient robustness…

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

The emergence of finetuning-as-a-service has revealed a new vulnerability in large language models (LLMs). A mere handful of malicious data uploaded by users can subtly manipulate the finetuning process, resulting in an alignment-broken…

Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…

Large language models (LLMs) have brought significant advancements to code generation, benefiting both novice and experienced developers. However, their training using unsanitized data from open-source repositories, like GitHub, introduces…

Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs). This paper delves into the mechanisms behind such successful…

In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety…

The remarkable performance of large language models (LLMs) in generation tasks has enabled practitioners to leverage publicly available models to power custom applications, such as chatbots and virtual assistants. However, the data used to…

Recent advancements in large language models (LLMs) have shown promising results in multilingual translation even with limited bilingual supervision. The major challenges are catastrophic forgetting and parameter interference for finetuning…

We present SEALion: an extensible framework for privacy-preserving machine learning with homomorphic encryption. It allows one to learn deep neural networks that can be seamlessly utilized for prediction on encrypted data. The framework…

Large language models (LLMs) are increasingly used for both open-ended and structured tasks, yet their inference-time behavior is still largely dictated by heuristic decoding strategies such as greedy search, sampling, or reranking. These…

Large Language Models (LLMs) have transformed natural language processing (NLP) by enabling robust text generation and understanding. However, their deployment in sensitive domains like healthcare, finance, and legal services raises…

In real-world deployments, Vision-Language Large Models (VLLMs) face critical challenges from multilingual and multimodal composite attacks: harmful images paired with low-resource language texts can easily bypass defenses designed for…

Large Language Models (LLMs) trained on massive data capture rich information embedded in the training data. However, this also introduces the risk of privacy leakage, particularly involving personally identifiable information (PII).…

Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature…

As machine learning (ML) systems are being increasingly employed in the real world to handle sensitive tasks and make decisions in various fields, the security and privacy of those models have also become increasingly critical. In…

Safety alignment is essential for the responsible deployment of large language models (LLMs). Yet, existing approaches often rely on heavyweight fine-tuning that is costly to update, audit, and maintain across model families. Full…

Multilingual safety remains significantly imbalanced, leaving non-high-resource (NHR) languages vulnerable compared to robust high-resource (HR) ones. Moreover, the neural mechanisms driving safety alignment remain unclear despite observed…

Large language models (LLMs) excel in various capabilities but pose safety risks such as generating harmful content and misinformation, even after safety alignment. In this paper, we explore the inner mechanisms of safety alignment through…