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...

Полное описание

Библиографические подробности
Главные авторы:	Lorenz, T, Kwiatkowska, M, Fritz, M
Формат:	Conference item
Язык:	English
Опубликовано:	Association for Computing Machinery 2023

Схожие документы

FullCert: deterministic end-to-end certification for training and inference of neural networks
по: Lorenz, T, и др.
Опубликовано: (2024)

Certified Robustness to Text Adversarial Attacks by Randomized [MASK]
по: Jiehang Zeng, и др.
Опубликовано: (2023-06-01)

Attack Vulnerability of Network Controllability.
по: Zhe-Ming Lu, и др.
Опубликовано: (2016-01-01)

Bayesian inference with certifiable adversarial robustness
по: Wicker, M, и др.
Опубликовано: (2021)

Vulnerability analysis on noise-injection based hardware attack on deep neural networks
по: Liu, Wenye, и др.
Опубликовано: (2020)

Uncertainty in vulnerability of networks under attack
по: Alireza Ermagun, и др.
Опубликовано: (2023-02-01)

Towards efficient and certified recovery from poisoning attacks in federated learning
по: Jiang, Yu, и др.
Опубликовано: (2025)

CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
по: Boopathy, Akhilan, и др.
Опубликовано: (2021)

Attacks, vulnerabilities and security requirements in smart metering networks
по: Abdullah, Muhammad Daniel Hafiz, и др.
Опубликовано: (2015)

Classification of Attacks in Simulation Studies of Complex Networks Vulnerabilities
по: A. A. Tikhomirov, и др.
Опубликовано: (2012-03-01)

Reachability computation for switching diffusions: finite abstractions with certifiable and tuneable precision
по: Laurenti, L, и др.
Опубликовано: (2017)

Reachability computation for switching diffusions: Finite abstractions with certifiable and tuneable precision
по: Laurenti, L, и др.
Опубликовано: (2017)

Backdoor attacks in neural networks
по: Low, Wen Wen
Опубликовано: (2023)

Backdoor attacks in neural networks
по: Liew, Sher Yun
Опубликовано: (2024)

Interdependency and vulnerability of multipartite networks under target node attacks
по: Cai, Qing, и др.
Опубликовано: (2020)

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

Interdependency and Vulnerability of Multipartite Networks under Target Node Attacks
по: Qing Cai, и др.
Опубликовано: (2019-01-01)

Automated Segmentation to Make Hidden Trigger Backdoor Attacks Robust against Deep Neural Networks
по: Saqib Ali, и др.
Опубликовано: (2023-04-01)

An assessment of the availability of cavities for secondary cavity-nesting birds in certified and conventionally-logged Neotropical rainforests
по: Schaaf AA, и др.
Опубликовано: (2020-08-01)

Demystifying adversarial attacks on neural networks
по: Yip, Lionell En Zhi
Опубликовано: (2020)

Adversarial attack defences for neural network
по: Singh Kirath
Опубликовано: (2022)

Adversarial attack defenses for neural networks
по: Puah, Yi Hao
Опубликовано: (2024)

Graph theory analysis reveals an assortative pain network vulnerable to attacks
по: Chong Chen, и др.
Опубликовано: (2023-12-01)

Examining indicators of complex network vulnerability across diverse attack scenarios
по: Ahmad F. Al Musawi, и др.
Опубликовано: (2023-10-01)

Vulnerability of Complex Networks under Approximate Longest Chain Attack Strategies
по: Hao Yao-Hui, и др.
Опубликовано: (2016-01-01)

Certified grasping
по: Aceituno-Cabezas, Bernardo, и др.
Опубликовано: (2024)

Certifiable AI
по: Jobst Landgrebe
Опубликовано: (2022-01-01)

Certified domination
по: Magda Dettlaff, и др.
Опубликовано: (2020-01-01)

Certified Computation
по: Arkoudas, Konstantine
Опубликовано: (2004)

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

Embedded Systems and their Vulnerabilities to Hardware Attacks
по: Konrad Szczepankiewicz, и др.
Опубликовано: (2023-03-01)

Vulnerability of blockchain technologies to quantum attacks
по: Joseph J. Kearney, и др.
Опубликовано: (2021-07-01)

Indoor environmental quality in WELL-certified and LEED-certified buildings
по: Michael G. Kent, и др.
Опубликовано: (2024-07-01)

Code Switching Used by Certified and Non-Certified English Teachers
по: Selvianillah Azis, и др.
Опубликовано: (2023-04-01)

SIL Loop: Certified or Non Certified Equipment — The Way to Go!
по: I P Parry, и др.
Опубликовано: (2002-12-01)

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

Assessment of water availability vulnerability in the Cerrado
по: Daniel Althoff, и др.
Опубликовано: (2021-10-01)

Investigating vulnerability of watermarking neural network
по: Chua, Viroy Sheng Yang
Опубликовано: (2020)

National Board-certified Teachers: Can They Make a Difference in Maine Schools?
по: Sarah V Mackenzie, и др.
Опубликовано: (2008-01-01)

Robustness guarantees for deep neural networks on videos
по: Kwiatkowska, M, и др.
Опубликовано: (2020)