-
公开(公告)号：US20230025731A1
公开(公告)日：2023-01-26
申请号：US17378794
申请日：2021-07-19
发明人： Michael Vinov , Oleg Blinder , Diptikalyan Saha , Sandeep Hans , Aniya Aggarwal , Omer Yehuda Boehm , Eyal Bin
摘要： A computer-implemented method comprising, automatically: analyzing a machine learning dataset which comprises multiple datapoints, to deduce constraints on features of the datapoints; generating a first set of CSP (Constraint Satisfaction Problem) rules expressing the constraints; based on a machine learning model which was trained on the dataset, generating a second set of CSP rules that define one or more perturbation candidates among the features of one of the datapoints; formulating a CSP based on the first and second sets of CSP rules; solving the formulated CSP using a solver; and using the solution of the CSP as a counterfactual explanation of a prediction made by the machine learning model with respect to the one datapoint.
-
公开(公告)号：US09576138B1
公开(公告)日：2017-02-21
申请号：US14870050
申请日：2015-09-30
CPC分类号： G06F21/55 , G06F3/0623 , G06F3/064 , G06F3/0673 , G06F12/0646 , G06F21/52 , G06F21/54 , G06F21/566 , G06F21/60 , G06F2212/1052 , G06N99/005
摘要： Mitigating return-oriented programming attacks. From program code and associated components needed by the program code for execution, machine language instruction sequences that may be combined and executed as malicious code are selected. A predetermined number of additional copies of each of the selected machine language instruction sequences are made, and the additional copies are marked as non-executable. The machine language instruction sequences and the non-executable copies are distributed in memory. If a process attempts to execute a machine language instruction sequence that has been marked non-executable, the computer may initiate protective action.
摘要翻译： 减轻面向回归的编程攻击。 从用于执行的程序代码所需的程序代码和相关组件中，选择可以组合和执行为恶意代码的机器语言指令序列。 制作每个所选机器语言指令序列的预定数目的附加副本，并且附加副本被标记为不可执行。 机器语言指令序列和不可执行副本分布在存储器中。 如果进程尝试执行已被标记为不可执行的机器语言指令序列，则计算机可能启动保护动作。
-
公开(公告)号：US20240176999A1
公开(公告)日：2024-05-30
申请号：US17994429
申请日：2022-11-28
发明人： Oleg Blinder , Omer Yehuda Boehm , LEV Greenberg , Michael Vinov
IPC分类号： G06N3/08
CPC分类号： G06N3/08
摘要： A computer-implemented method including: training a first Generative Adversarial Network (GAN) based on original structured data; training a second GAN based on fabricated structured data that adhere to user-defined constraints; combining the first and second GANs into a combined GAN; training the combined GAN; and operating the trained combined GAN to generate new fabricated data that both imitate characteristics of the original structured data, and adhere to the user-defined constraints.
-
公开(公告)号：US09734329B2
公开(公告)日：2017-08-15
申请号：US15132739
申请日：2016-04-19
CPC分类号： G06F21/55 , G06F3/0623 , G06F3/064 , G06F3/0673 , G06F12/0646 , G06F21/52 , G06F21/54 , G06F21/566 , G06F21/60 , G06F2212/1052 , G06N99/005
摘要： Mitigating return-oriented programming attacks. From program code and associated components needed by the program code for execution, machine language instruction sequences that may be combined and executed as malicious code are selected. A predetermined number of additional copies of each of the selected machine language instruction sequences are made, and the additional copies are marked as non-executable. The machine language instruction sequences and the non-executable copies are distributed in memory. If a process attempts to execute a machine language instruction sequence that has been marked non-executable, the computer may initiate protective action.
-
公开(公告)号：US20200228339A1
公开(公告)日：2020-07-16
申请号：US16244138
申请日：2019-01-10
发明人： Muhammad Barham , Ariel Farkash , Ron Shmelkin , Omri Soceanu , Michael Vinov
摘要： Embodiments of the present systems and methods may provide encrypted biometric information that can be stored and used for authentication with undegraded recognition performance. For example, in an embodiment, a method may comprise storing a plurality of encrypted trained weights of a neural network classifier, wherein the weights have been trained using biometric information representing at least one biometric feature of a person, receiving encrypted biometric information obtained by sampling at least one biometric feature of the person and encrypting the sampled biometric feature, obtaining an match-score using the encrypted trained neural network classifier, the match-score indicating a probability that the received encrypted biometric information matches the stored encrypted biometric information, and authenticating the person when the probability that received encrypted biometric information matches the stored encrypted biometric information exceeds a threshold.
-
公开(公告)号：US20170091456A1
公开(公告)日：2017-03-30
申请号：US15263782
申请日：2016-09-13
CPC分类号： G06F21/55 , G06F3/0623 , G06F3/064 , G06F3/0673 , G06F12/0646 , G06F21/52 , G06F21/54 , G06F21/566 , G06F21/60 , G06F2212/1052 , G06N99/005
摘要： Mitigating return-oriented programming (ROP) attacks. Program code and associated components are received and loaded into memory. From the program code and associated components, a predetermined number of sequences of machine language instructions that terminate in a return instruction are selected. The sequences of machine language instructions include: machine language instruction sequences that are equivalent to a conditional statement “if-then-else return,” sequences of machine language instructions corresponding to known malicious code sequences, and sequences of machine language instructions corresponding to machine language instructions in known toolkits for assembling malicious code sequences. For each selected machine language instruction sequence, memory blocks containing the selected machine language instruction sequence are rearranged using address space layout randomization (ASLR); then, upon expiration of an expected time interval required to locate the selected machine language instruction sequence by inspecting the rearranged memory blocks, the rearranging is repeated, thereby mitigating ROP attacks.
-
公开(公告)号：US20170091447A1
公开(公告)日：2017-03-30
申请号：US15264672
申请日：2016-09-14
CPC分类号： G06F21/55 , G06F3/0623 , G06F3/064 , G06F3/0673 , G06F12/0646 , G06F21/52 , G06F21/54 , G06F21/566 , G06F21/60 , G06F2212/1052 , G06N99/005
摘要： Mitigating return-oriented programming attacks. Program code and associated components are received and loaded into memory. From the program code and associated components, a predetermined number of sequences of machine language instructions that terminate in a return instruction are selected. The sequences of machine language instructions include: machine language instruction sequences that are equivalent to a conditional statement “if-then-else return,” sequences of machine language instructions corresponding to known malicious code sequences, and sequences of machine language instructions corresponding to machine language instructions in known toolkits for assembling malicious code sequences. For each selected machine language instruction sequence, memory blocks containing the selected machine language instruction sequence are rearranged using address space layout randomization (ASLR); then, upon expiration of an expected time interval required to locate the selected machine language instruction sequence by inspecting the rearranged memory blocks, the rearranging is repeated, thereby mitigating ROP attacks.
-
公开(公告)号：US11201745B2
公开(公告)日：2021-12-14
申请号：US16244138
申请日：2019-01-10
发明人： Muhammad Barham , Ariel Farkash , Ron Shmelkin , Omri Soceanu , Michael Vinov
摘要： Embodiments of the present systems and methods may provide encrypted biometric information that can be stored and used for authentication with undegraded recognition performance. For example, in an embodiment, a method may comprise storing a plurality of encrypted trained weights of a neural network classifier, wherein the weights have been trained using biometric information representing at least one biometric feature of a person, receiving encrypted biometric information obtained by sampling at least one biometric feature of the person and encrypting the sampled biometric feature, obtaining an match-score using the encrypted trained neural network classifier, the match-score indicating a probability that the received encrypted biometric information matches the stored encrypted biometric information, and authenticating the person when the probability that received encrypted biometric information matches the stored encrypted biometric information exceeds a threshold.
-
公开(公告)号：US09665717B2
公开(公告)日：2017-05-30
申请号：US15263782
申请日：2016-09-13
CPC分类号： G06F21/55 , G06F3/0623 , G06F3/064 , G06F3/0673 , G06F12/0646 , G06F21/52 , G06F21/54 , G06F21/566 , G06F21/60 , G06F2212/1052 , G06N99/005
摘要： Mitigating return-oriented programming (ROP) attacks. Program code and associated components are received and loaded into memory. From the program code and associated components, a predetermined number of sequences of machine language instructions that terminate in a return instruction are selected. The sequences of machine language instructions include: machine language instruction sequences that are equivalent to a conditional statement “if-then-else return,” sequences of machine language instructions corresponding to known malicious code sequences, and sequences of machine language instructions corresponding to machine language instructions in known toolkits for assembling malicious code sequences. For each selected machine language instruction sequence, memory blocks containing the selected machine language instruction sequence are rearranged using address space layout randomization (ASLR); then, upon expiration of an expected time interval required to locate the selected machine language instruction sequence by inspecting the rearranged memory blocks, the rearranging is repeated, thereby mitigating ROP attacks.
-
公开(公告)号：US20170091449A1
公开(公告)日：2017-03-30
申请号：US15132739
申请日：2016-04-19
CPC分类号： G06F21/55 , G06F3/0623 , G06F3/064 , G06F3/0673 , G06F12/0646 , G06F21/52 , G06F21/54 , G06F21/566 , G06F21/60 , G06F2212/1052 , G06N99/005
摘要： Mitigating return-oriented programming attacks. From program code and associated components needed by the program code for execution, machine language instruction sequences that may be combined and executed as malicious code are selected. A predetermined number of additional copies of each of the selected machine language instruction sequences are made, and the additional copies are marked as non-executable. The machine language instruction sequences and the non-executable copies are distributed in memory. If a process attempts to execute a machine language instruction sequence that has been marked non-executable, the computer may initiate protective action.
-
-
-
-
-
-
-
-
-
搜索结果
11 条记录 (耗时 0.019 秒)
