Tianwei Zhang

Stealing Deep Reinforcement Learning Models for Fun and Profit

2020 · arXiv (Cornell University)

This paper presents the first model extraction attack against Deep Reinforcement Learning (DRL), which enables an external adversary to precisely recover a black-box DRL model only from its interaction with the environment. Model extraction attacks …

DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation

2021

Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However, if the third-party providers are untrusted, they can inject poisoned samples into …

Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models

2021

Watermarking has become the tendency in protecting the intellectual property of DNN models. Recent works, from the adversary's perspective, attempted to subvert watermarking mechanisms by designing watermark removal attacks. However, these attacks mainly adopted sophisticated …

A General Framework for Defending Against Backdoor Attacks via Influence Graph

2021 · arXiv (Cornell University)

In this work, we propose a new and general framework to defend against backdoor attacks, inspired by the fact that attack triggers usually follow a \textsc{specific} type of attacking pattern, and therefore, poisoned training examples …

SIMC 2.0: Improved Secure ML Inference Against Malicious Clients

2022 · arXiv (Cornell University)

In this paper, we study the problem of secure ML inference against a malicious client and a semi-trusted server such that the client only learns the inference output while the server learns nothing. This problem …

Incremental Learning, Incremental Backdoor Threats

2022 · IEEE Transactions on Dependable and Secure Computing

Class incremental learning from a pre-trained DNN model is gaining lots of popularity. Unfortunately, the pre-trained model also introduces a new attack vector, which enables an adversary to inject a backdoor into it and further …

GPT-NER: Named Entity Recognition via Large Language Models

2023 · arXiv (Cornell University)

Despite the fact that large-scale Language Models (LLM) have achieved SOTA performances on a variety of NLP tasks, its performance on NER is still significantly below supervised baselines. This is due to the gap between …

PriFR: Privacy-preserving Large-scale File Retrieval System via Blockchain for Encrypted Cloud Data

2023

As a fundamental and commonly used service, file retrieval has been extensively studied by information retrieval, cryptography, and big data communities. In this paper, we consider the problem of privacy-preserving file retrieval. A new framework …

Pushing the Limits of ChatGPT on NLP Tasks

2023 · arXiv (Cornell University)

Despite the success of ChatGPT, its performances on most NLP tasks are still well below the supervised baselines. In this work, we looked into the causes, and discovered that its subpar performance was caused by …

AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA

2024 · arXiv (Cornell University)

Diffusion models have achieved remarkable success in generating high-quality images. Recently, the open-source models represented by Stable Diffusion (SD) are thriving and are accessible for customization, giving rise to a vibrant community of creators and …

Papers by this author