no code implementations • 2 Oct 2024 • Yanming Liu, Xinyue Peng, Jiannan Cao, Shi Bo, Yanxin Shen, Xuhong Zhang, Sheng Cheng, Xun Wang, Jianwei Yin, Tianyu Du
Large language models (LLMs) have shown remarkable capabilities in natural language processing; however, they still face difficulties when tasked with understanding lengthy contexts and executing effective question answering.
1 code implementation • 2 Sep 2024 • Rui Zeng, Xi Chen, Yuwen Pu, Xuhong Zhang, Tianyu Du, Shouling Ji
CLIBE injects a "few-shot perturbation" into the suspect Transformer model by crafting optimized weight perturbation in the attention layers to make the perturbed model classify a limited number of reference samples as a target label.
no code implementations • 25 Jun 2024 • Tianyu Du, Ayush Kanodia, Herman Brunborg, Keyon Vafa, Susan Athey
For the task of next job prediction, we demonstrate that models trained with our approach outperform several alternatives in terms of predictive performance on the survey data, including traditional econometric models, CAREER, and LLMs with in-context learning, even though the LLM can in principle predict job titles that are not allowed in the survey data.
no code implementations • 16 Jun 2024 • Yanming Liu, Xinyue Peng, Yuwei Zhang, Xiaolan Ke, Songhang Deng, Jiannan Cao, Chen Ma, Mengchen Fu, Xuhong Zhang, Sheng Cheng, Xun Wang, Jianwei Yin, Tianyu Du
In this paper, we introduce DP-MemArc, a novel training framework aimed at reducing the memory costs of large language models while emphasizing the protection of user data privacy.
1 code implementation • 6 Jun 2024 • Yanming Liu, Xinyue Peng, Jiannan Cao, Shi Bo, Yuwei Zhang, Xuhong Zhang, Sheng Cheng, Xun Wang, Jianwei Yin, Tianyu Du
Experiments show that our approach demonstrates a high pass and win rate across different datasets and optimizes the planning scheme for tool learning in models such as GPT-4 and Claude 3, showcasing the potential of our method.
no code implementations • 9 May 2024 • Zhe Ma, Xuhong Zhang, Qingming Li, Tianyu Du, Wenzhi Chen, Zonghui Wang, Shouling Ji
Based on the correlation, we propose to utilize inversion techniques to verify the safety of target images against memorization and measure the extent to which they are memorized.
no code implementations • 17 Apr 2024 • Qinfeng Li, Zhiqiang Shen, Zhenghan Qin, Yangfan Xie, Xuhong Zhang, Tianyu Du, Jianwei Yin
Specifically, we identify four critical protection properties that existing methods fail to simultaneously satisfy: (1) maintaining protection after a model is physically copied; (2) authorizing model access at request level; (3) safeguarding runtime reverse engineering; (4) achieving high security with negligible runtime overhead.
1 code implementation • 11 Mar 2024 • Yanming Liu, Xinyue Peng, Tianyu Du, Jianwei Yin, Weihao Liu, Xuhong Zhang
Large language models (LLMs) have achieved commendable accomplishments in various natural language processing tasks.
1 code implementation • 11 Mar 2024 • Yanming Liu, Xinyue Peng, Xuhong Zhang, Weihao Liu, Jianwei Yin, Jiannan Cao, Tianyu Du
Large language models (LLMs) demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters.
1 code implementation • NeurIPS 2023 • Ziyi Yin, Muchao Ye, Tianrong Zhang, Tianyu Du, Jinguo Zhu, Han Liu, Jinghui Chen, Ting Wang, Fenglong Ma
In this paper, we aim to investigate a new yet practical task to craft image and text perturbations using pre-trained VL models to attack black-box fine-tuned models on different downstream tasks.
1 code implementation • 25 Sep 2023 • Tianyu Du, Luca Melis, Ting Wang
We present ReMasker, a new method of imputing missing values in tabular data by extending the masked autoencoding framework.
no code implementations • 8 Jun 2023 • Hao Yu, Chuan Ma, Meng Liu, Tianyu Du, Ming Ding, Tao Xiang, Shouling Ji, Xinwang Liu
Through empirical evaluation, comparing G$^2$uardFL with cutting-edge defenses, such as FLAME (USENIX Security 2022) [28] and DeepSight (NDSS 2022) [36], against various backdoor attacks including 3DFed (SP 2023) [20], our results demonstrate its significant effectiveness in mitigating backdoor attacks while having a negligible impact on the aggregated model's performance on benign samples (i. e., the primary task performance).
1 code implementation • 3 May 2023 • Zhaohan Xi, Tianyu Du, Changjiang Li, Ren Pang, Shouling Ji, Xiapu Luo, Xusheng Xiao, Fenglong Ma, Ting Wang
Knowledge graph reasoning (KGR) -- answering complex logical queries over large knowledge graphs -- represents an important artificial intelligence task, entailing a range of applications (e. g., cyber threat hunting).
no code implementations • 17 Apr 2023 • Yunruo Zhang, Tianyu Du, Shouling Ji, Peng Tang, Shanqing Guo
In this paper, we propose the first certified defense against multi-frame attacks for RNNs called RNN-Guard.
1 code implementation • 4 Apr 2023 • Tianyu Du, Ayush Kanodia, Susan Athey
$\texttt{torch-choice}$ provides a $\texttt{ChoiceDataset}$ data structure to manage databases flexibly and memory-efficiently.
3 code implementations • ICCV 2023 • Changjiang Li, Ren Pang, Zhaohan Xi, Tianyu Du, Shouling Ji, Yuan YAO, Ting Wang
As a new paradigm in machine learning, self-supervised learning (SSL) is capable of learning high-quality representations of complex data without relying on labels.
no code implementations • 27 Sep 2022 • Zhaohan Xi, Ren Pang, Changjiang Li, Tianyu Du, Shouling Ji, Fenglong Ma, Ting Wang
(ii) It supports complex logical queries with varying relation and view constraints (e. g., with complex topology and/or from multiple views); (iii) It scales up to KGs of large sizes (e. g., millions of facts) and fine-granular views (e. g., dozens of views); (iv) It generalizes to query structures and KG views that are unobserved during training.
2 code implementations • 15 Aug 2022 • Jiaxuan You, Tianyu Du, Jure Leskovec
Finally, we propose a scalable and efficient training approach for dynamic GNNs via incremental training and meta-learning.
1 code implementation • 16 Feb 2022 • Keyon Vafa, Emil Palikot, Tianyu Du, Ayush Kanodia, Susan Athey, David M. Blei
We fit CAREER to a dataset of 24 million job sequences from resumes, and adjust it on small longitudinal survey datasets.
1 code implementation • 25 Dec 2021 • Haibin Zheng, Zhiqing Chen, Tianyu Du, Xuhong Zhang, Yao Cheng, Shouling Ji, Jingyi Wang, Yue Yu, Jinyin Chen
To overcome the challenges, we propose NeuronFair, a new DNN fairness testing framework that differs from previous work in several key aspects: (1) interpretable - it quantitatively interprets DNNs' fairness violations for the biased decision; (2) effective - it uses the interpretation results to guide the generation of more diverse instances in less time; (3) generic - it can handle both structured and unstructured data.
no code implementations • 23 Feb 2021 • Jinfeng Li, Tianyu Du, Xiangyu Liu, Rong Zhang, Hui Xue, Shouling Ji
Extensive experiments on two real-world tasks show that AdvGraph exhibits better performance compared with previous work: (i) effective - it significantly strengthens the model robustness even under the adaptive attacks setting without negative impact on model performance over legitimate input; (ii) generic - its key component, i. e., the representation of connotative adversarial knowledge is task-agnostic, which can be reused in any Chinese-based NLP models without retraining; and (iii) efficient - it is a light-weight defense with sub-linear computational complexity, which can guarantee the efficiency required in practical scenarios.
no code implementations • 23 Jan 2019 • Tianyu Du, Shouling Ji, Jinfeng Li, Qinchen Gu, Ting Wang, Raheem Beyah
Despite their immense popularity, deep learning-based acoustic systems are inherently vulnerable to adversarial attacks, wherein maliciously crafted audios trigger target systems to misbehave.
Cryptography and Security
1 code implementation • 13 Dec 2018 • Jinfeng Li, Shouling Ji, Tianyu Du, Bo Li, Ting Wang
Deep Learning-based Text Understanding (DLTU) is the backbone technique behind various applications, including question answering, machine translation, and text classification.