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...

Deskribapen osoa

Xehetasun bibliografikoak
Egile Nagusiak:	Lorenz, T, Kwiatkowska, M, Fritz, M
Formatua:	Conference item
Hizkuntza:	English
Argitaratua:	Association for Computing Machinery 2023

Antzeko izenburuak

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

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

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

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

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

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

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

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

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

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

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

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

Backdoor attacks in neural networks
nork: Low, Wen Wen
Argitaratua: (2023)

Backdoor attacks in neural networks
nork: Liew, Sher Yun
Argitaratua: (2024)

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

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

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

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

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

Demystifying adversarial attacks on neural networks
nork: Yip, Lionell En Zhi
Argitaratua: (2020)

Adversarial attack defences for neural network
nork: Singh Kirath
Argitaratua: (2022)

Adversarial attack defenses for neural networks
nork: Puah, Yi Hao
Argitaratua: (2024)

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

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

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

Certified grasping
nork: Aceituno-Cabezas, Bernardo, et al.
Argitaratua: (2024)

Certifiable AI
nork: Jobst Landgrebe
Argitaratua: (2022-01-01)

Certified domination
nork: Magda Dettlaff, et al.
Argitaratua: (2020-01-01)

Certified Computation
nork: Arkoudas, Konstantine
Argitaratua: (2004)

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

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

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

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

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

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

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

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

Investigating vulnerability of watermarking neural network
nork: Chua, Viroy Sheng Yang
Argitaratua: (2020)

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

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