09 2023 档案
摘要:Title Adaptive restart for stochastic synthesis PLDI 2021 Task Distribute the power between multiple runs in stochastic program synthesis to accelerat
阅读全文
摘要:## Abstract 背景:Compiling DNN models into high-efficiency executables is not easy: the compilation procedure often involves converting high-level model
阅读全文
摘要:## Abstract 背景:深度学习编译器处理的深度学习模型与命令式程序有根本的不同,因为深度学习模型中的程序逻辑是隐式的。(the DL models processed by DL compilers differ fundamentally from imperative programs
阅读全文
摘要:## Abstract 本文:DeepMutation Github: https://github.com/berkuva/mutation-testing-for-DNNs Task: mutation testing framework specialized for DL systems t
阅读全文
摘要:## Abstract 本文: Task: Testing the classification accuracy of a deep learning framework that includes a CNN Method: 1. classifier built with SVM 2. met
阅读全文
摘要:## Abstract 本文: Task: Fuzzing Machine Learning Libraries Method: 1. optimized mutation strategies 2. prioritize the seed 3. optimal mutation strategy
阅读全文
摘要:## Abstract 本文:DeepCover Github: https://github.com/TrustAI/DeepCover Task: propose 4 novel test criteria to test DNNs Method: inspired by MC/DC cover
阅读全文
摘要:## Abstract 本文:SparseProp Github: https://github.com/IST-DASLab/sparseprop Task: a back-propagation algo for sparse training data, a fast vectorized i
阅读全文
摘要:## Abstract 本文: PyTorch Task: detail the implementation and architecture of PyTorch Github: https://github.com/pytorch/pytorch 特点: 1. PyTorch同时关注可用性和速
阅读全文
摘要:## Abstract 本文: Task: Review on the use of LLMs in software testing Method: 1. analyzes 52 relevant studies ## 1. Intro  to induce misclassifi
阅读全文
摘要:## Abstract 本文: BTD github: https://github.com/monkbai/DNN-decompiler/ Task: a decompiler for DNN models to output DNN specifications including: opera
阅读全文
摘要:## Abstract 背景:In fact, some of the latest findings suggest that the existence of adversarial attacks may be an inherent weakness of deep learning mod
阅读全文
摘要:## Abstract 背景:The correctness of DL systems is crucial for trust in DL applications 本文: NeuRI BaseTool: FreeFuzz Github: https://github.com/ise-uiuc/
阅读全文
摘要:## Abstract 背景:目前大多数的adversarial attack method on pre-trained models of code忽略了perturbations should be natural to human judges(naturalness requirement
阅读全文
摘要:## Abstract 背景:已有的方法(Muffin, Lemon, Cradle) can cover at most 34.1% layer inputs, 25.9% layer parameter values, and 15.6% layer sequences. 本文:COMET Gi
阅读全文
摘要:## Abstract 本文:IvySyn Task: discover memory error vulnerabilities in DL frameworks BugType: memory safety errors, fatal runtime errors Method: 1. 利用na
阅读全文
摘要:## Abstract 本文: Task: 1. prove invariance-inducing regularizers can increase predictive accuracy for worst-case spatial transformations 2. prove that
阅读全文
摘要:## Abstract 本文: Task: 1. study the faithfulness of an explanation system to the underlying prediction model on consistency and sufficiency 2. introduc
阅读全文
摘要:## Abstract 背景:目前对cross-framework conversion中的inconsistencies和security bugs的研究少有 本文:TensorScope Github: https://github.com/tensorscopepro/Tensorscope
阅读全文
摘要:## Abstract 本文: DeepTest Task: a systematic testing tool for DNN-driven vehicles Method: 1. generated test cases with real-world changes like rain, fo
阅读全文
摘要:## Abstract 本文: DeepGauge Task: provide multi-granularity testing criteria for DL systems Method: multi-granularity testing criteria for DL systems: 1
阅读全文
摘要:## Abstract 本文:DeepCT Task: Testing DL Models with Combinatorial Testing Method: 1. 将输出值的空间离散化为区间,以便覆盖每个区间,对不同层内的神经元交互进⾏采样,并减少必须执⾏的测试输⼊的数量。 2. a set o
阅读全文
摘要:## Abstract 本文:描述automatic differentiation module of PyTorch 包括:Lua Torch, Chainer, HIPS Autograd Task: Provides a high-performance environment on dif
阅读全文
摘要:## Abstract Github: https://github.com/shijy16/ACETest 背景: 1. DL operators 用来计算多维tensors,很重要 本文:ACETest Task: automatically extract input validation c
阅读全文