相关论文: Gracefully Filtering Backdoor Samples for Generati…

Despite large language models (LLMs) have achieved impressive achievements across numerous tasks, supervised fine-tuning (SFT) remains essential for adapting these models to specialized domains. However, SFT for domain specialization can be…

Federated Prompt Learning has emerged as a communication-efficient and privacy-preserving paradigm for adapting large vision-language models like CLIP across decentralized clients. However, the security implications of this setup remain…

In-context learning (ICL) has demonstrated remarkable success in large language models (LLMs) due to its adaptability and parameter-free nature. However, it also introduces a critical vulnerability to backdoor attacks, where adversaries can…

Deep neural networks have achieved remarkable success across various applications; however, their vulnerability to backdoor attacks poses severe security risks -- especially in situations where only a limited set of clean samples is…

Despite the widespread use of statistical prior models in various fields, such models for neural network gradients have long been overlooked. The inherent challenge stems from their high-dimensional structures and complex interdependencies,…

Data privacy has become an increasingly important issue in Machine Learning (ML), where many approaches have been developed to tackle this challenge, e.g. cryptography (Homomorphic Encryption (HE), Differential Privacy (DP), etc.) and…

Current backdoor attacks against federated learning (FL) strongly rely on universal triggers or semantic patterns, which can be easily detected and filtered by certain defense mechanisms such as norm clipping, comparing parameter…

Large language models (LLMs) have revolutionized lots of fields of research. Although it is well-known that fine-tuning is essential for enhancing the capabilities of LLMs, existing research suggests that there is potential redundancy in…

In this paper, we present a new form of backdoor attack against Large Language Models (LLMs): lingual-backdoor attacks. The key novelty of lingual-backdoor attacks is that the language itself serves as the trigger to hijack the infected…

Large Language Models (LLMs) are known for their expensive and time-consuming training. Thus, oftentimes, LLMs are fine-tuned to address a specific task, given the pretrained weights of a pre-trained LLM considered a foundation model. In…

Intrusion Detection Systems (IDS) play a crucial role in network security defense. However, a significant challenge for IDS in training detection models is the shortage of adequately labeled malicious samples. To address these issues, this…

Federated Learning (FL) framework brings privacy benefits to distributed learning systems by allowing multiple clients to participate in a learning task under the coordination of a central server without exchanging their private data.…

Federated Contrastive Learning (FCL) is an emerging privacy-preserving paradigm in distributed learning for unlabeled data. In FCL, distributed parties collaboratively learn a global encoder with unlabeled data, and the global encoder could…

We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive Language Models (RLMs), a general inference paradigm that treats long prompts as part of an…

We explore the ability of large language models (LLMs) to act as speech recognition post-processors that perform rescoring and error correction. Our first focus is on instruction prompting to let LLMs perform these task without fine-tuning,…

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…

Large language models (LLMs) have convincing performance in a variety of downstream tasks. However, these systems are prone to generating undesirable outputs such as harmful and biased text. In order to remedy such generations, the…

Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the…

Addressing the critical need for robust safety in Large Language Models (LLMs), particularly against adversarial attacks and in-distribution errors, we introduce Reinforcement Learning with Backtracking Feedback (RLBF). This framework…

The self-attention revolution allowed generative language models to scale and achieve increasingly impressive abilities. Such models - commonly referred to as Large Language Models (LLMs) - have recently gained prominence with the general…