Cover Image

Position: Certified Robustness Does Not (Yet) Imply Model Security

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cullen, Andrew C., Montague, Paul, Erfani, Sarah M., Rubinstein, Benjamin I. P.
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks
by: Liu, Shijie, et al.
Published: (2023)

Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
by: Cullen, Andrew C., et al.
Published: (2023)

CERT-ED: Certifiably Robust Text Classification for Edit Distance
by: Huang, Zhuoqun, et al.
Published: (2024)

AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
by: Huang, Zhuoqun, et al.
Published: (2025)

Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning
by: Liu, Shijie, et al.
Published: (2025)

HALO: Robust Out-of-Distribution Detection via Joint Optimisation
by: Keenan, Hugo Lyons, et al.
Published: (2025)

Certified but Fooled! Breaking Certified Defences with Ghost Certificates
by: Vo, Quoc Viet, et al.
Published: (2025)

Getting a-Round Guarantees: Floating-Point Attacks on Certified Robustness
by: Jin, Jiankai, et al.
Published: (2022)

RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion
by: Huang, Zhuoqun, et al.
Published: (2023)

One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy
by: Zhang, Jiacheng, et al.
Published: (2025)

Augment then Smooth: Reconciling Differential Privacy with Certified Robustness
by: Wu, Jiapeng, et al.
Published: (2023)

On Using Certified Training towards Empirical Robustness
by: De Palma, Alessandro, et al.
Published: (2024)

Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning
by: Liu, Shijie, et al.
Published: (2025)

Collective Certified Robustness against Graph Injection Attacks
by: Lai, Yuni, et al.
Published: (2024)

Towards Generalized Certified Robustness with Multi-Norm Training
by: Jiang, Enyi, et al.
Published: (2024)

End-to-End Anti-Backdoor Learning on Images and Time Series
by: Jiang, Yujing, et al.
Published: (2024)

The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Models
by: Dolatabadi, Hadi M., et al.
Published: (2023)

Certified Causal Defense with Generalizable Robustness
by: Qiao, Yiran, et al.
Published: (2024)

CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximization
by: Wang, Derui, et al.
Published: (2025)

Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
by: Lyu, Saiyue, et al.
Published: (2024)

A Robust Certified Machine Unlearning Method Under Distribution Shift
by: Guo, Jinduo, et al.
Published: (2026)

Certified Robust Accuracy of Neural Networks Are Bounded due to Bayes Errors
by: Zhang, Ruihan, et al.
Published: (2024)

Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models
by: Arcos-Holzinger, Sandra, et al.
Published: (2026)

Are We There Yet? Timing and Floating-Point Attacks on Differential Privacy Systems
by: Jin, Jiankai, et al.
Published: (2021)

Robust Privacy: Inference-Time Privacy through Certified Robustness
by: Jin, Jiankai, et al.
Published: (2026)

Robustness Implies Privacy in Statistical Estimation
by: Hopkins, Samuel B., et al.
Published: (2022)

Certifiably Robust RAG against Retrieval Corruption
by: Xiang, Chong, et al.
Published: (2024)

Certified Unlearning for Neural Networks
by: Koloskova, Anastasia, et al.
Published: (2025)

Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates
by: Angioni, Daniele, et al.
Published: (2024)

Towards Certified Malware Detection: Provable Guarantees Against Evasion Attacks
by: Giri, Nandakrishna, et al.
Published: (2026)

Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
by: Wang, Xiaobao, et al.
Published: (2025)

Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs
by: Salem, Ahmed, et al.
Published: (2026)

Adversarial Robustness on Image Classification with $k$-means
by: Omari, Rollin, et al.
Published: (2023)

CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models
by: Lou, Qian, et al.
Published: (2024)

Certified Defense on the Fairness of Graph Neural Networks
by: Dong, Yushun, et al.
Published: (2023)

Cross-Input Certified Training for Universal Perturbations
by: Xu, Changming, et al.
Published: (2024)

Towards Strong Certified Defense with Universal Asymmetric Randomization
by: Hong, Hanbin, et al.
Published: (2025)

SLVR: Securely Leveraging Client Validation for Robust Federated Learning
by: Choi, Jihye, et al.
Published: (2025)

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills
by: Hsu, Chia-Yi, et al.
Published: (2026)

Certifiably Robust Image Watermark
by: Jiang, Zhengyuan, et al.
Published: (2024)