paper-with-me

홈 › Papers

Prompt Backdoors in Visual Prompt Learning

2023-10-11 · Hai Huang, Zhengyu Zhao, Michael Backes, Yun Shen, Yang Zhang

Fine-tuning large pre-trained computer vision models is infeasible for resource-limited users. Visual prompt learning (VPL) has thus emerged to provide an efficient and flexible alternative to model fine-tuning through Visual Prompt as a Service (VPPTaaS). Specifically, the VPPTaaS provider optimizes a visual prompt given downstream data, and downstream users can use this prompt together with the large pre-trained model for prediction. However, this new learning paradigm may also pose security risks when the VPPTaaS provider instead provides a malicious visual prompt. In this paper, we take the first step to explore such risks through the lens of backdoor attacks. Specifically, we propose BadVisualPrompt, a simple yet effective backdoor attack against VPL. For example, poisoning $5\%$ CIFAR10 training data leads to above $99\%$ attack success rates with only negligible model accuracy drop by $1.5\%$. In particular, we identify and then address a new technical challenge related to interactions between the backdoor trigger and visual prompt, which does not exist in conventional, model-level backdoors. Moreover, we provide in-depth analyses of seven backdoor defenses from model, prompt, and input levels. Overall, all these defenses are either ineffective or impractical to mitigate our BadVisualPrompt, implying the critical vulnerability of VPL.

📄 PDF Abstract BibTeX arXiv:2310.07632

Code (0)

등록된 구현이 없습니다.

Tasks

Backdoor AttackPrompt Learning

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Similar Papers 제목 키워드 기반

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models

2024-11-14 · Zi-Xuan Huang, Jia-Wei Chen, Zhi-Peng Zhang, Chia-Mu Yu

Visual prompting (VP) is a new technique that adapts well-trained frozen models for source domain tasks to target domain tasks. This study examines VP's benefits for black-box model-level backdoor detection. The visual p…

Visual Prompting

LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors

2023-08-26 · Chengkun Wei, Wenlong Meng, Zhikun Zhang, Min Chen 외

Prompt-tuning has emerged as an attractive paradigm for deploying large-scale language models due to its strong downstream task performance and efficient multitask serving ability. Despite its wide adoption, we empirical…

Universal Jailbreak Backdoors from Poisoned Human Feedback

2023-11-24 · Javier Rando, Florian Tramèr

Reinforcement Learning from Human Feedback (RLHF) is used to align large language models to produce helpful and harmless responses. Yet, prior work showed these models can be jailbroken by finding adversarial prompts tha…

Backdoor Attack

NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models

2023-05-28 · Kai Mei, Zheng Li, Zhenting Wang, Yang Zhang 외

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be …

AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment

2024-10-15 · Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Furong Huang

With the growing adoption of reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs), the risk of backdoor installation during alignment has increased, leading to unintended and harmfu…