Related papers: FedAPT: Federated Adversarial Prompt Tuning for Vi…
Federated Learning (FL) is a distributed machine learning (ML) paradigm, in which multiple clients collaboratively train ML models without centralizing their local data. Similar to conventional ML pipelines, the client local optimization…
Prompt learning has emerged as an efficient alternative to fine-tuning pre-trained vision-language models (VLMs). Despite its promise, current methods still struggle to maintain tail-class discriminability when adapting to class-imbalanced…
Prompt Tuning, conditioning on task-specific learned prompt vectors, has emerged as a data-efficient and parameter-efficient method for adapting large pretrained vision-language models to multiple downstream tasks. However, existing…
Federated learning is a promising distributed machine learning paradigm that can effectively exploit large-scale data without exposing users' privacy. However, it may incur significant communication overhead, thereby potentially impairing…
This paper documents early research conducted in 2022 on defending against prompt injection attacks in large language models, providing historical context for the evolution of this critical security domain. This research focuses on two…
Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle…
Prompt learning has become a prevalent strategy for adapting vision-language foundation models (VLMs) such as CLIP to downstream tasks. With the emergence of large language models (LLMs), recent studies have explored the potential of using…
Vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot capabilities for various downstream tasks. Their performance can be further enhanced through few-shot prompt tuning methods. However, current studies…
Fine-tuning large language models (LLMs) often causes overfitting to specific prompt wording, where minor phrasing variations drastically reduce performance. To address this, we propose Prompt-Agnostic Fine-Tuning (PAFT), a method that…
The task of medical image recognition is notably complicated by the presence of varied and multiple pathological indications, presenting a unique challenge in multi-label classification with unseen labels. This complexity underlines the…
Benefiting from prompt tuning, recent years have witnessed the promising performance of pre-trained vision-language models, e.g., CLIP, on versatile downstream tasks. In this paper, we focus on a particular setting of learning adaptive…
Federated learning (FL) has emerged to enable global model training over distributed clients' data while preserving its privacy. However, the global trained model is vulnerable to the evasion attacks especially, the adversarial examples…
Federated Parameter-Efficient Fine-Tuning (Fed-PEFT) enables lightweight adaptation of large pre-trained models in federated learning settings by updating only a small subset of parameters. However, Fed-PEFT methods typically assume a fixed…
Fine-grained entity typing (FET) is an essential task in natural language processing that aims to assign semantic types to entities in text. However, FET poses a major challenge known as the noise labeling problem, whereby current methods…
Graph prompt tuning has shown great potential in graph learning by introducing trainable prompts to enhance the model performance in conventional single-domain scenarios. Recent research has extended graph prompts to improve Graph…
Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive capability in visual tasks, but their fine-tuning often suffers from bias in class-imbalanced scene. Recent works have introduced large language models…
Context: Software vulnerabilities pose a significant threat to modern software systems, as evidenced by the growing number of reported vulnerabilities and cyberattacks. These escalating trends underscore the urgent need for effective…
Large pre-trained vision-language models (VLMs) offer a promising approach to leveraging human language for enhancing downstream tasks. However, VLMs such as CLIP face significant limitation: its performance is highly sensitive to prompt…
Federated learning (FL) is a feasible technique to learn personalized recommendation models from decentralized user data. Unfortunately, federated recommender systems are vulnerable to poisoning attacks by malicious clients. Existing…
Recent progress has shown great potential of visual prompt tuning (VPT) when adapting pre-trained vision transformers to various downstream tasks. However, most existing solutions independently optimize prompts at each layer, thereby…