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.
no code implementations • 6 May 2024 • Chengxin Zhao, Hefei Ling, Sijing Xie, Han Fang, Yaokun Fang, Nan Sun
Modern image processing tools have made it easy for attackers to crop the region or object of interest in images and paste it into other images.
no code implementations • 18 Apr 2024 • Han Fang, Xianghao Zang, Chao Ban, Zerun Feng, Lanxiang Zhou, Zhongjiang He, Yongxiang Li, Hao Sun
Text-video retrieval aims to find the most relevant cross-modal samples for a given query.
1 code implementation • 7 Apr 2024 • Zijin Yang, Kai Zeng, Kejiang Chen, Han Fang, Weiming Zhang, Nenghai Yu
To address this issue, we propose Gaussian Shading, a diffusion model watermarking technique that is both performance-lossless and training-free, while serving the dual purpose of copyright protection and tracing of offending content.
no code implementations • 21 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.
no code implementations • 7 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.
no code implementations • 4 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.
no code implementations • 18 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.
1 code implementation • 30 Oct 2023 • Tianwen Wei, Liang Zhao, Lichang Zhang, Bo Zhu, Lijie Wang, Haihua Yang, Biye Li, Cheng Cheng, Weiwei Lü, Rui Hu, Chenxia Li, Liu Yang, Xilin Luo, Xuejie Wu, Lunan Liu, Wenjun Cheng, Peng Cheng, Jianhao Zhang, XiaoYu Zhang, Lei Lin, Xiaokun Wang, Yutuan Ma, Chuanhai Dong, Yanqi Sun, Yifu Chen, Yongyi Peng, Xiaojuan Liang, Shuicheng Yan, Han Fang, Yahui Zhou
In this technical report, we present Skywork-13B, a family of large language models (LLMs) trained on a corpus of over 3. 2 trillion tokens drawn from both English and Chinese texts.
1 code implementation • 27 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.
no code implementations • 2 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.
1 code implementation • 14 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.
no code implementations • 13 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.
no code implementations • 10 May 2023 • Jiyi Zhang, Han Fang, Hwee Kuan Lee, Ee-Chien Chang
Our goal is to select a set of samples from the corpus for the given model.
no code implementations • 26 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.
1 code implementation • 4 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.
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.
no code implementations • 4 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.
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.
no code implementations • 2 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.
no code implementations • 13 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.
no code implementations • 7 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.
no code implementations • 30 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.
no code implementations • 19 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
no code implementations • 13 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.
Ranked #1 on Face Recognition on MLFW
1 code implementation • 18 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.
no code implementations • 5 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.
1 code implementation • 21 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 #11 on Video Retrieval on VATEX (using extra training data)
3 code implementations • 29 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.
Ranked #1 on Topic Classification on OS
no code implementations • 15 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.
15 code implementations • 8 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.
1 code implementation • 25 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.
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.