Search Results for author: Han Fang

Found 30 papers, 10 papers with code

Generate to Adapt: Resolution Adaption Network for Surveillance Face Recognition

no code implementations ECCV 2020 Han Fang, Weihong Deng, Yaoyao Zhong, Jiani Hu

Although deep learning techniques have largely improved face recognition, unconstrained surveillance face recognition (FR) is still an unsolved challenge, due to the limited training data and the gap of domain distribution.

Face Recognition Translation

Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs

no code implementations21 Feb 2024 Xiaoxia Li, Siyuan Liang, Jiyi Zhang, Han Fang, Aishan Liu, Ee-Chien Chang

Large Language Models (LLMs), used in creative writing, code generation, and translation, generate text based on input sequences but are vulnerable to jailbreak attacks, where crafted prompts induce harmful outputs.

Code Generation Semantic Similarity +1

Domain Bridge: Generative model-based domain forensic for black-box models

no code implementations7 Feb 2024 Jiyi Zhang, Han Fang, Ee-Chien Chang

In forensic investigations of machine learning models, techniques that determine a model's data domain play an essential role, with prior work relying on large-scale corpora like ImageNet to approximate the target model's domain.

INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer

no code implementations4 Feb 2024 Han Fang, Zhihao Song, Paul Weng, Yutong Ban

Recently, deep reinforcement learning has shown promising results for learning fast heuristics to solve routing problems.

Improving Adversarial Transferability by Stable Diffusion

no code implementations18 Nov 2023 Jiayang Liu, Siyu Zhu, Siyuan Liang, Jie Zhang, Han Fang, Weiming Zhang, Ee-Chien Chang

Various techniques have emerged to enhance the transferability of adversarial attacks for the black-box scenario.

Effective Long-Context Scaling of Foundation Models

1 code implementation27 Sep 2023 Wenhan Xiong, Jingyu Liu, Igor Molybog, Hejia Zhang, Prajjwal Bhargava, Rui Hou, Louis Martin, Rashi Rungta, Karthik Abinav Sankararaman, Barlas Oguz, Madian Khabsa, Han Fang, Yashar Mehdad, Sharan Narang, Kshitiz Malik, Angela Fan, Shruti Bhosale, Sergey Edunov, Mike Lewis, Sinong Wang, Hao Ma

We also examine the impact of various design choices in the pretraining process, including the data mix and the training curriculum of sequence lengths -- our ablation experiments suggest that having abundant long texts in the pretrain dataset is not the key to achieving strong performance, and we empirically verify that long context continual pretraining is more efficient and similarly effective compared to pretraining from scratch with long sequences.

Continual Pretraining Language Modelling

Adaptive Attractors: A Defense Strategy against ML Adversarial Collusion Attacks

no code implementations2 Jun 2023 Jiyi Zhang, Han Fang, Ee-Chien Chang

This induces different adversarial regions in different copies, making adversarial samples generated on one copy not replicable on others.

Watermarking Text Generated by Black-Box Language Models

1 code implementation14 May 2023 Xi Yang, Kejiang Chen, Weiming Zhang, Chang Liu, Yuang Qi, Jie Zhang, Han Fang, Nenghai Yu

To allow third-parties to autonomously inject watermarks into generated text, we develop a watermarking framework for black-box language model usage scenarios.

Adversarial Robustness Language Modelling +2

Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval

no code implementations13 May 2023 Han Fang, Zhifei Yang, Xianghao Zang, Chao Ban, Hao Sun

Specifically, after applying attention-based video masking to generate high-informed and low-informed masks, we propose Informed Semantics Completion to recover masked semantics information.

Retrieval Text Retrieval +1

Multi-objective Generative Design of Three-Dimensional Composite Materials

no code implementations26 Feb 2023 Zhengyang Zhang, Han Fang, Zhao Xu, Jiajie Lv, Yao Shen, Yanming Wang

Composite materials with 3D architectures are desirable in a variety of applications for the capability of tailoring their properties to meet multiple functional requirements.

Generative Adversarial Network

Representation Deficiency in Masked Language Modeling

no code implementations4 Feb 2023 Yu Meng, Jitin Krishnan, Sinong Wang, Qifan Wang, Yuning Mao, Han Fang, Marjan Ghazvininejad, Jiawei Han, Luke Zettlemoyer

In this work, we offer a new perspective on the consequence of such a discrepancy: We demonstrate empirically and theoretically that MLM pretraining allocates some model dimensions exclusively for representing $\texttt{[MASK]}$ tokens, resulting in a representation deficiency for real tokens and limiting the pretrained model's expressiveness when it is adapted to downstream data without $\texttt{[MASK]}$ tokens.

Language Modelling Masked Language Modeling

Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence

no code implementations ICCV 2023 Han Fang, Jiyi Zhang, Yupeng Qiu, Ke Xu, Chengfang Fang, Ee-Chien Chang

In this paper, we take the role of investigators who want to trace the attack and identify the source, that is, the particular model which the adversarial examples are generated from.

Adversarial Attack

Improved Adaptive Algorithm for Scalable Active Learning with Weak Labeler

no code implementations4 Nov 2022 Yifang Chen, Karthik Sankararaman, Alessandro Lazaric, Matteo Pirotta, Dmytro Karamshuk, Qifan Wang, Karishma Mandyam, Sinong Wang, Han Fang

We design a novel algorithmic template, Weak Labeler Active Cover (WL-AC), that is able to robustly leverage the lower quality weak labelers to reduce the query complexity while retaining the desired level of accuracy.

Active Learning

PIMoG: An Effective Screen-shooting Noise-Layer Simulation for Deep-Learning-Based Watermarking Network

1 code implementation MM '22: Proceedings of the 30th ACM International Conference on Multimedia 2022 Han Fang

In order to design an effective noise layer for screen-shooting robustness, we propose new insight in this paper, that is, it is not necessary to quantitatively simulate the overall procedure in the screen-shooting noise layer, only including the most influenced distortions is enough to generate an effective noise layer with strong robustness.

BayesFormer: Transformer with Uncertainty Estimation

no code implementations2 Jun 2022 Karthik Abinav Sankararaman, Sinong Wang, Han Fang

Transformer has become ubiquitous due to its dominant performance in various NLP and image processing tasks.

Active Learning Language Modelling +3

Conditional Variational Autoencoder with Balanced Pre-training for Generative Adversarial Networks

no code implementations13 Jan 2022 Yuchong Yao, Xiaohui Wangr, Yuanbang Ma, Han Fang, Jiaying Wei, Liyuan Chen, Ali Anaissi, Ali Braytee

The two recent methods, Balancing GAN (BAGAN) and improved BAGAN (BAGAN-GP), are proposed as an augmentation tool to handle this problem and restore the balance to the data.

Image Classification

Reducing Target Group Bias in Hate Speech Detectors

no code implementations7 Dec 2021 Darsh J Shah, Sinong Wang, Han Fang, Hao Ma, Luke Zettlemoyer

The ubiquity of offensive and hateful content on online fora necessitates the need for automatic solutions that detect such content competently across target groups.

text-classification Text Classification

Mitigating Adversarial Attacks by Distributing Different Copies to Different Users

no code implementations30 Nov 2021 Jiyi Zhang, Han Fang, Wesley Joon-Wie Tann, Ke Xu, Chengfang Fang, Ee-Chien Chang

We point out that by distributing different copies of the model to different buyers, we can mitigate the attack such that adversarial samples found on one copy would not work on another copy.

Speech Pattern based Black-box Model Watermarking for Automatic Speech Recognition

no code implementations19 Oct 2021 Haozhe Chen, Weiming Zhang, Kunlin Liu, Kejiang Chen, Han Fang, Nenghai Yu

As an effective method for intellectual property (IP) protection, model watermarking technology has been applied on a wide variety of deep neural networks (DNN), including speech classification models.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

MLFW: A Database for Face Recognition on Masked Faces

no code implementations13 Sep 2021 Chengrui Wang, Han Fang, Yaoyao Zhong, Weihong Deng

As more and more people begin to wear masks due to current COVID-19 pandemic, existing face recognition systems may encounter severe performance degradation when recognizing masked faces.

Face Recognition

MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression

1 code implementation18 Aug 2021 Zhaoyang Jia, Han Fang, Weiming Zhang

To address such limitations, we proposed a novel end-to-end training architecture, which utilizes Mini-Batch of Real and Simulated JPEG compression (MBRS) to enhance the JPEG robustness.

Exploring Structure Consistency for Deep Model Watermarking

no code implementations5 Aug 2021 Jie Zhang, Dongdong Chen, Jing Liao, Han Fang, Zehua Ma, Weiming Zhang, Gang Hua, Nenghai Yu

However, little attention has been devoted to the protection of DNNs in image processing tasks.

Data Augmentation

CLIP2Video: Mastering Video-Text Retrieval via Image CLIP

1 code implementation21 Jun 2021 Han Fang, Pengfei Xiong, Luhui Xu, Yu Chen

We present CLIP2Video network to transfer the image-language pre-training model to video-text retrieval in an end-to-end manner.

Ranked #10 on Video Retrieval on VATEX (using extra training data)

Language Modelling Retrieval +3

Entailment as Few-Shot Learner

3 code implementations29 Apr 2021 Sinong Wang, Han Fang, Madian Khabsa, Hanzi Mao, Hao Ma

Large pre-trained language models (LMs) have demonstrated remarkable ability as few-shot learners.

Contrastive Learning Data Augmentation +8

Micro-Estimates of Wealth for all Low- and Middle-Income Countries

no code implementations15 Apr 2021 Guanghua Chi, Han Fang, Sourav Chatterjee, Joshua E. Blumenstock

Many critical policy decisions, from strategic investments to the allocation of humanitarian aid, rely on data about the geographic distribution of wealth and poverty.

Humanitarian

Linformer: Self-Attention with Linear Complexity

15 code implementations8 Jun 2020 Sinong Wang, Belinda Z. Li, Madian Khabsa, Han Fang, Hao Ma

Large transformer models have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications.

Language Modelling

Model Watermarking for Image Processing Networks

1 code implementation25 Feb 2020 Jie Zhang, Dong-Dong Chen, Jing Liao, Han Fang, Weiming Zhang, Wenbo Zhou, HAO CUI, Nenghai Yu

In this way, when the attacker trains one surrogate model by using the input-output pairs of the target model, the hidden watermark will be learned and extracted afterward.

DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense

1 code implementation ICCV 2019 Hang Zhou, Kejiang Chen, Weiming Zhang, Han Fang, Wenbo Zhou, Nenghai Yu

We propose a Denoiser and UPsampler Network (DUP-Net) structure as defenses for 3D adversarial point cloud classification, where the two modules reconstruct surface smoothness by dropping or adding points.

Denoising Point Cloud Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.