DeCE: Deceptive Cross-Entropy Loss Designed for Defending Backdoor
Attacks

DeCE: Deceptive Cross-Entropy Loss Designed for Defending Backdoor Attacks

12 July 2024

David Lo

Papers citing "DeCE: Deceptive Cross-Entropy Loss Designed for Defending Backdoor Attacks"

6 / 6 papers shown

Title
Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation Jiawei Liu Chun Xia Yuyao Wang Lingming Zhang ELM ALM 172 388 0 02 May 2023
ICE-Score: Instructing Large Language Models to Evaluate Code Terry Yue Zhuo ELM ALM 34 38 0 27 Apr 2023
Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code Changan Niu Chuanyi Li Bin Luo Vincent Ng SyDa VLM 36 48 0 24 May 2022
CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation Yue Wang Weishi Wang Shafiq R. Joty S. Hoi 201 1,451 0 02 Sep 2021
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation Shuai Lu Daya Guo Shuo Ren Junjie Huang Alexey Svyatkovskiy ... Nan Duan Neel Sundaresan Shao Kun Deng Shengyu Fu Shujie Liu ELM 190 853 0 09 Feb 2021
Mitigating backdoor attacks in LSTM-based Text Classification Systems by Backdoor Keyword Identification Chuanshuai Chen Jiazhu Dai SILM 48 126 0 11 Jul 2020