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...

書誌詳細
主要な著者:	Lorenz, T, Kwiatkowska, M, Fritz, M
フォーマット:	Conference item
言語:	English
出版事項:	Association for Computing Machinery 2023

類似資料

FullCert: deterministic end-to-end certification for training and inference of neural networks
著者:: Lorenz, T, 等
出版事項: (2024)

Certified Robustness to Text Adversarial Attacks by Randomized [MASK]
著者:: Jiehang Zeng, 等
出版事項: (2023-06-01)

Attack Vulnerability of Network Controllability.
著者:: Zhe-Ming Lu, 等
出版事項: (2016-01-01)

Bayesian inference with certifiable adversarial robustness
著者:: Wicker, M, 等
出版事項: (2021)

Vulnerability analysis on noise-injection based hardware attack on deep neural networks
著者:: Liu, Wenye, 等
出版事項: (2020)

Uncertainty in vulnerability of networks under attack
著者:: Alireza Ermagun, 等
出版事項: (2023-02-01)

Towards efficient and certified recovery from poisoning attacks in federated learning
著者:: Jiang, Yu, 等
出版事項: (2025)

CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
著者:: Boopathy, Akhilan, 等
出版事項: (2021)

Attacks, vulnerabilities and security requirements in smart metering networks
著者:: Abdullah, Muhammad Daniel Hafiz, 等
出版事項: (2015)

Classification of Attacks in Simulation Studies of Complex Networks Vulnerabilities
著者:: A. A. Tikhomirov, 等
出版事項: (2012-03-01)

Reachability computation for switching diffusions: finite abstractions with certifiable and tuneable precision
著者:: Laurenti, L, 等
出版事項: (2017)

Reachability computation for switching diffusions: Finite abstractions with certifiable and tuneable precision
著者:: Laurenti, L, 等
出版事項: (2017)

Backdoor attacks in neural networks
著者:: Low, Wen Wen
出版事項: (2023)

Backdoor attacks in neural networks
著者:: Liew, Sher Yun
出版事項: (2024)

Interdependency and vulnerability of multipartite networks under target node attacks
著者:: Cai, Qing, 等
出版事項: (2020)

Detection of vulnerability attack through wireless network on android platform
著者:: Muhamad Izhan Fakri, Imran
出版事項: (2014)

Interdependency and Vulnerability of Multipartite Networks under Target Node Attacks
著者:: Qing Cai, 等
出版事項: (2019-01-01)

Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks
著者:: Saqib Ali, 等
出版事項: (2023-04-01)

An assessment of the availability of cavities for secondary cavity-nesting birds in certified and conventionally-logged Neotropical rainforests
著者:: Schaaf AA, 等
出版事項: (2020-08-01)

Demystifying adversarial attacks on neural networks
著者:: Yip, Lionell En Zhi
出版事項: (2020)

Adversarial attack defences for neural network
著者:: Singh Kirath
出版事項: (2022)

Adversarial attack defenses for neural networks
著者:: Puah, Yi Hao
出版事項: (2024)

Graph theory analysis reveals an assortative pain network vulnerable to attacks
著者:: Chong Chen, 等
出版事項: (2023-12-01)

Examining indicators of complex network vulnerability across diverse attack scenarios
著者:: Ahmad F. Al Musawi, 等
出版事項: (2023-10-01)

Vulnerability of Complex Networks under Approximate Longest Chain Attack Strategies
著者:: Hao Yao-Hui, 等
出版事項: (2016-01-01)

Certified grasping
著者:: Aceituno-Cabezas, Bernardo, 等
出版事項: (2024)

Certifiable AI
著者:: Jobst Landgrebe
出版事項: (2022-01-01)

Certified domination
著者:: Magda Dettlaff, 等
出版事項: (2020-01-01)

Certified Computation
著者:: Arkoudas, Konstantine
出版事項: (2004)

Safety verification for deep neural networks with provable guarantees
著者:: Kwiatkowska, M
出版事項: (2019)

Embedded Systems and their Vulnerabilities to Hardware Attacks
著者:: Konrad Szczepankiewicz, 等
出版事項: (2023-03-01)

Vulnerability of blockchain technologies to quantum attacks
著者:: Joseph J. Kearney, 等
出版事項: (2021-07-01)

Indoor environmental quality in WELL-certified and LEED-certified buildings
著者:: Michael G. Kent, 等
出版事項: (2024-07-01)

Code Switching Used by Certified and Non-Certified English Teachers
著者:: Selvianillah Azis, 等
出版事項: (2023-04-01)

SIL Loop: Certified or Non Certified Equipment — The Way to Go!
著者:: I P Parry, 等
出版事項: (2002-12-01)

Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks.
著者:: Hokuto Hirano, 等
出版事項: (2020-01-01)

Assessment of water availability vulnerability in the Cerrado
著者:: Daniel Althoff, 等
出版事項: (2021-10-01)

Investigating vulnerability of watermarking neural network
著者:: Chua, Viroy Sheng Yang
出版事項: (2020)

National Board-certified Teachers: Can They Make a Difference in Maine Schools?
著者:: Sarah V Mackenzie, 等
出版事項: (2008-01-01)

Robustness guarantees for deep neural networks on videos
著者:: Kwiatkowska, M, 等
出版事項: (2020)