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...

Descripció completa

Dades bibliogràfiques
Autors principals:	Lorenz, T, Kwiatkowska, M, Fritz, M
Format:	Conference item
Idioma:	English
Publicat:	Association for Computing Machinery 2023

Ítems similars

FullCert: deterministic end-to-end certification for training and inference of neural networks
per: Lorenz, T, et al.
Publicat: (2024)

Certified Robustness to Text Adversarial Attacks by Randomized [MASK]
per: Jiehang Zeng, et al.
Publicat: (2023-06-01)

Attack Vulnerability of Network Controllability.
per: Zhe-Ming Lu, et al.
Publicat: (2016-01-01)

Bayesian inference with certifiable adversarial robustness
per: Wicker, M, et al.
Publicat: (2021)

Vulnerability analysis on noise-injection based hardware attack on deep neural networks
per: Liu, Wenye, et al.
Publicat: (2020)

Uncertainty in vulnerability of networks under attack
per: Alireza Ermagun, et al.
Publicat: (2023-02-01)

Towards efficient and certified recovery from poisoning attacks in federated learning
per: Jiang, Yu, et al.
Publicat: (2025)

CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
per: Boopathy, Akhilan, et al.
Publicat: (2021)

Attacks, vulnerabilities and security requirements in smart metering networks
per: Abdullah, Muhammad Daniel Hafiz, et al.
Publicat: (2015)

Classification of Attacks in Simulation Studies of Complex Networks Vulnerabilities
per: A. A. Tikhomirov, et al.
Publicat: (2012-03-01)

Reachability computation for switching diffusions: finite abstractions with certifiable and tuneable precision
per: Laurenti, L, et al.
Publicat: (2017)

Reachability computation for switching diffusions: Finite abstractions with certifiable and tuneable precision
per: Laurenti, L, et al.
Publicat: (2017)

Backdoor attacks in neural networks
per: Low, Wen Wen
Publicat: (2023)

Backdoor attacks in neural networks
per: Liew, Sher Yun
Publicat: (2024)

Interdependency and vulnerability of multipartite networks under target node attacks
per: Cai, Qing, et al.
Publicat: (2020)

Detection of vulnerability attack through wireless network on android platform
per: Muhamad Izhan Fakri, Imran
Publicat: (2014)

Interdependency and Vulnerability of Multipartite Networks under Target Node Attacks
per: Qing Cai, et al.
Publicat: (2019-01-01)

Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks
per: Saqib Ali, et al.
Publicat: (2023-04-01)

An assessment of the availability of cavities for secondary cavity-nesting birds in certified and conventionally-logged Neotropical rainforests
per: Schaaf AA, et al.
Publicat: (2020-08-01)

Demystifying adversarial attacks on neural networks
per: Yip, Lionell En Zhi
Publicat: (2020)

Adversarial attack defences for neural network
per: Singh Kirath
Publicat: (2022)

Adversarial attack defenses for neural networks
per: Puah, Yi Hao
Publicat: (2024)

Graph theory analysis reveals an assortative pain network vulnerable to attacks
per: Chong Chen, et al.
Publicat: (2023-12-01)

Examining indicators of complex network vulnerability across diverse attack scenarios
per: Ahmad F. Al Musawi, et al.
Publicat: (2023-10-01)

Vulnerability of Complex Networks under Approximate Longest Chain Attack Strategies
per: Hao Yao-Hui, et al.
Publicat: (2016-01-01)

Certified grasping
per: Aceituno-Cabezas, Bernardo, et al.
Publicat: (2024)

Certifiable AI
per: Jobst Landgrebe
Publicat: (2022-01-01)

Certified domination
per: Magda Dettlaff, et al.
Publicat: (2020-01-01)

Certified Computation
per: Arkoudas, Konstantine
Publicat: (2004)

Safety verification for deep neural networks with provable guarantees
per: Kwiatkowska, M
Publicat: (2019)

Embedded Systems and their Vulnerabilities to Hardware Attacks
per: Konrad Szczepankiewicz, et al.
Publicat: (2023-03-01)

Vulnerability of blockchain technologies to quantum attacks
per: Joseph J. Kearney, et al.
Publicat: (2021-07-01)

Indoor environmental quality in WELL-certified and LEED-certified buildings
per: Michael G. Kent, et al.
Publicat: (2024-07-01)

Code Switching Used by Certified and Non-Certified English Teachers
per: Selvianillah Azis, et al.
Publicat: (2023-04-01)

SIL Loop: Certified or Non Certified Equipment — The Way to Go!
per: I P Parry, et al.
Publicat: (2002-12-01)

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

Assessment of water availability vulnerability in the Cerrado
per: Daniel Althoff, et al.
Publicat: (2021-10-01)

Investigating vulnerability of watermarking neural network
per: Chua, Viroy Sheng Yang
Publicat: (2020)

National Board-certified Teachers: Can They Make a Difference in Maine Schools?
per: Sarah V Mackenzie, et al.
Publicat: (2008-01-01)

Robustness guarantees for deep neural networks on videos
per: Kwiatkowska, M, et al.
Publicat: (2020)