no code implementations • 5 Mar 2024 • ZiHao Wang, Rui Zhu, Dongruo Zhou, Zhikun Zhang, John Mitchell, Haixu Tang, XiaoFeng Wang
DPAdapter modifies and enhances the sharpness-aware minimization (SAM) technique, utilizing a two-batch strategy to provide a more accurate perturbation estimate and an efficient gradient descent, thereby improving parameter robustness against noise.
no code implementations • 24 Oct 2023 • Xiaoyi Chen, Siyuan Tang, Rui Zhu, Shijun Yan, Lei Jin, ZiHao Wang, Liya Su, XiaoFeng Wang, Haixu Tang
In the attack, one can construct a PII association task, whereby an LLM is fine-tuned using a minuscule PII dataset, to potentially reinstate and reveal concealed PIIs.
no code implementations • 28 Sep 2023 • Xiaotian Zhou, Qian Wang, XiaoFeng Wang, Haixu Tang, Xiaozhong Liu
Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks.
no code implementations • 29 Jan 2023 • Rui Zhu, Di Tang, Siyuan Tang, Guanhong Tao, Shiqing Ma, XiaoFeng Wang, Haixu Tang
Finally, we perform both theoretical and experimental analysis, showing that the GRASP enhancement does not reduce the effectiveness of the stealthy attacks against the backdoor detection methods based on weight analysis, as well as other backdoor mitigation methods without using detection.
no code implementations • 9 Dec 2022 • Rui Zhu, Di Tang, Siyuan Tang, XiaoFeng Wang, Haixu Tang
Our idea is to retrain a given DNN model on randomly labeled clean data, to induce a CF on the model, leading to a sudden forget on both primary and backdoor tasks; then we recover the primary task by retraining the randomized model on correctly labeled clean data.
no code implementations • 12 Oct 2022 • Di Tang, Rui Zhu, XiaoFeng Wang, Haixu Tang, Yi Chen
With extensive studies on backdoor attack and detection, still fundamental questions are left unanswered regarding the limits in the adversary's capability to attack and the defender's capability to detect.
1 code implementation • ResearchSquare 2022 • Kaiyuan Liu, Yuzhen Ye, Haixu Tang
The de novo peptide sequencing, which does not rely on a comprehensive target sequence database, provided us a way to identify novel peptides from tandem mass (MS/MS) spectra.
no code implementations • 14 Jul 2020 • Rui Zhu, Bo Lin, Haixu Tang
In this paper, we present the first method to estimate the upper bound of the number of linear regions in any sphere in the input space of a given ReLU neural network.
no code implementations • 4 Mar 2020 • Tongxin Wang, Zhengming Ding, Wei Shao, Haixu Tang, Kun Huang
Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions.
1 code implementation • 2 Aug 2019 • Di Tang, Xiao-Feng Wang, Haixu Tang, Kehuan Zhang
A security threat to deep neural networks (DNN) is backdoor contamination, in which an adversary poisons the training data of a target model to inject a Trojan so that images carrying a specific trigger will always be classified into a specific label.
Cryptography and Security
1 code implementation • 13 Feb 2018 • Yunhui Long, Vincent Bindschaedler, Lei Wang, Diyue Bu, Xiao-Feng Wang, Haixu Tang, Carl A. Gunter, Kai Chen
Membership Inference Attack (MIA) determines the presence of a record in a machine learning model's training data by querying the model.