Certifiers make neural networks vulnerable to availability attacks

Certifiers make neural networks vulnerable to availability attacks

To achieve reliable, robust, and safe AI systems, it is vital to implement fallback strategies when AI predictions cannot be trusted. Certifiers for neural networks are a reliable way to check the robustness of these predictions. They guarantee for some predictions that a certain class of manipulati...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй
Үндсэн зохиолчид:	Lorenz, T, Kwiatkowska, M, Fritz, M
Формат:	Conference item
Хэл сонгох:	English
Хэвлэсэн:	Association for Computing Machinery 2023

Ижил төстэй зүйлс

FullCert: deterministic end-to-end certification for training and inference of neural networks
-н: Lorenz, T, зэрэг
Хэвлэсэн: (2024)

Certified Robustness to Text Adversarial Attacks by Randomized [MASK]
-н: Jiehang Zeng, зэрэг
Хэвлэсэн: (2023-06-01)

Attack Vulnerability of Network Controllability.
-н: Zhe-Ming Lu, зэрэг
Хэвлэсэн: (2016-01-01)

Bayesian inference with certifiable adversarial robustness
-н: Wicker, M, зэрэг
Хэвлэсэн: (2021)

Vulnerability analysis on noise-injection based hardware attack on deep neural networks
-н: Liu, Wenye, зэрэг
Хэвлэсэн: (2020)

Uncertainty in vulnerability of networks under attack
-н: Alireza Ermagun, зэрэг
Хэвлэсэн: (2023-02-01)

Towards efficient and certified recovery from poisoning attacks in federated learning
-н: Jiang, Yu, зэрэг
Хэвлэсэн: (2025)

CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
-н: Boopathy, Akhilan, зэрэг
Хэвлэсэн: (2021)

Attacks, vulnerabilities and security requirements in smart metering networks
-н: Abdullah, Muhammad Daniel Hafiz, зэрэг
Хэвлэсэн: (2015)

Classification of Attacks in Simulation Studies of Complex Networks Vulnerabilities
-н: A. A. Tikhomirov, зэрэг
Хэвлэсэн: (2012-03-01)

Reachability computation for switching diffusions: finite abstractions with certifiable and tuneable precision
-н: Laurenti, L, зэрэг
Хэвлэсэн: (2017)

Reachability computation for switching diffusions: Finite abstractions with certifiable and tuneable precision
-н: Laurenti, L, зэрэг
Хэвлэсэн: (2017)

Backdoor attacks in neural networks
-н: Low, Wen Wen
Хэвлэсэн: (2023)

Backdoor attacks in neural networks
-н: Liew, Sher Yun
Хэвлэсэн: (2024)

Interdependency and vulnerability of multipartite networks under target node attacks
-н: Cai, Qing, зэрэг
Хэвлэсэн: (2020)

Detection of vulnerability attack through wireless network on android platform
-н: Muhamad Izhan Fakri, Imran
Хэвлэсэн: (2014)

Interdependency and Vulnerability of Multipartite Networks under Target Node Attacks
-н: Qing Cai, зэрэг
Хэвлэсэн: (2019-01-01)

Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks
-н: Saqib Ali, зэрэг
Хэвлэсэн: (2023-04-01)

An assessment of the availability of cavities for secondary cavity-nesting birds in certified and conventionally-logged Neotropical rainforests
-н: Schaaf AA, зэрэг
Хэвлэсэн: (2020-08-01)

Demystifying adversarial attacks on neural networks
-н: Yip, Lionell En Zhi
Хэвлэсэн: (2020)

Adversarial attack defences for neural network
-н: Singh Kirath
Хэвлэсэн: (2022)

Adversarial attack defenses for neural networks
-н: Puah, Yi Hao
Хэвлэсэн: (2024)

Graph theory analysis reveals an assortative pain network vulnerable to attacks
-н: Chong Chen, зэрэг
Хэвлэсэн: (2023-12-01)

Examining indicators of complex network vulnerability across diverse attack scenarios
-н: Ahmad F. Al Musawi, зэрэг
Хэвлэсэн: (2023-10-01)

Vulnerability of Complex Networks under Approximate Longest Chain Attack Strategies
-н: Hao Yao-Hui, зэрэг
Хэвлэсэн: (2016-01-01)

Certified grasping
-н: Aceituno-Cabezas, Bernardo, зэрэг
Хэвлэсэн: (2024)

Certifiable AI
-н: Jobst Landgrebe
Хэвлэсэн: (2022-01-01)

Certified domination
-н: Magda Dettlaff, зэрэг
Хэвлэсэн: (2020-01-01)

Certified Computation
-н: Arkoudas, Konstantine
Хэвлэсэн: (2004)

Safety verification for deep neural networks with provable guarantees
-н: Kwiatkowska, M
Хэвлэсэн: (2019)

Embedded Systems and their Vulnerabilities to Hardware Attacks
-н: Konrad Szczepankiewicz, зэрэг
Хэвлэсэн: (2023-03-01)

Vulnerability of blockchain technologies to quantum attacks
-н: Joseph J. Kearney, зэрэг
Хэвлэсэн: (2021-07-01)

Indoor environmental quality in WELL-certified and LEED-certified buildings
-н: Michael G. Kent, зэрэг
Хэвлэсэн: (2024-07-01)

Code Switching Used by Certified and Non-Certified English Teachers
-н: Selvianillah Azis, зэрэг
Хэвлэсэн: (2023-04-01)

SIL Loop: Certified or Non Certified Equipment — The Way to Go!
-н: I P Parry, зэрэг
Хэвлэсэн: (2002-12-01)

Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks.
-н: Hokuto Hirano, зэрэг
Хэвлэсэн: (2020-01-01)

Assessment of water availability vulnerability in the Cerrado
-н: Daniel Althoff, зэрэг
Хэвлэсэн: (2021-10-01)

Investigating vulnerability of watermarking neural network
-н: Chua, Viroy Sheng Yang
Хэвлэсэн: (2020)

National Board-certified Teachers: Can They Make a Difference in Maine Schools?
-н: Sarah V Mackenzie, зэрэг
Хэвлэсэн: (2008-01-01)

Robustness guarantees for deep neural networks on videos
-н: Kwiatkowska, M, зэрэг
Хэвлэсэн: (2020)