Copertina

Certified but Fooled! Breaking Certified Defences with Ghost Certificates

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Vo, Quoc Viet, Haq, Tashreque M., Montague, Paul, Abraham, Tamas, Abbasnejad, Ehsan, Ranasinghe, Damith C.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Cryptography and Security Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack
di: Vo, Viet Quoc, et al.
Pubblicazione: (2024)

Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness
di: Deng, Jieren, et al.
Pubblicazione: (2024)

Bayesian Learned Models Can Detect Adversarial Malware For Free
di: Doan, Bao Gia, et al.
Pubblicazione: (2024)

Certifiably Robust Image Watermark
di: Jiang, Zhengyuan, et al.
Pubblicazione: (2024)

StyleFool: Fooling Video Classification Systems via Style Transfer
di: Cao, Yuxin, et al.
Pubblicazione: (2022)

On the Credibility of Backdoor Attacks Against Object Detectors in the Physical World
di: Doan, Bao Gia, et al.
Pubblicazione: (2024)

PromptSmooth: Certifying Robustness of Medical Vision-Language Models via Prompt Learning
di: Hussein, Noor, et al.
Pubblicazione: (2024)

Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attacks
di: Hao, Run, et al.
Pubblicazione: (2025)

PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses
di: Xiang, Chong, et al.
Pubblicazione: (2023)

Certified Robustness to Data Poisoning in Gradient-Based Training
di: Sosnin, Philip, et al.
Pubblicazione: (2024)

Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising
di: Hong, Sanghyun, et al.
Pubblicazione: (2024)

COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks
di: Huang, Zijian, et al.
Pubblicazione: (2024)

ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs
di: Yang, Yuchen, et al.
Pubblicazione: (2024)

LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer
di: Cao, Yuxin, et al.
Pubblicazione: (2023)

FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distribution
di: Zhou, Qi, et al.
Pubblicazione: (2024)

PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches
di: Jacob, Dennis, et al.
Pubblicazione: (2025)

RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance
di: Lin, Miao, et al.
Pubblicazione: (2026)

Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
di: Shpilevskiy, Frederick, et al.
Pubblicazione: (2025)

Cert-SSBD: Certified Backdoor Defense with Sample-Specific Smoothing Noises
di: Qiao, Ting, et al.
Pubblicazione: (2025)

Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness
di: Jang, Suhyeok, et al.
Pubblicazione: (2024)

CertDW: Towards Certified Dataset Ownership Verification via Conformal Prediction
di: Qiao, Ting, et al.
Pubblicazione: (2025)

Technical Report for ICML 2024 TiFA Workshop MLLM Attack Challenge: Suffix Injection and Projected Gradient Descent Can Easily Fool An MLLM
di: Guo, Yangyang, et al.
Pubblicazione: (2024)

Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks
di: Qraitem, Maan, et al.
Pubblicazione: (2024)

Transparency Attacks: How Imperceptible Image Layers Can Fool AI Perception
di: McKee, Forrest, et al.
Pubblicazione: (2024)

Fooling the Image Dehazing Models by First Order Gradient
di: Gui, Jie, et al.
Pubblicazione: (2023)

Can a Teenager Fool an AI? Evaluating Low-Cost Cosmetic Attacks on Age Estimation Systems
di: Shen, Xingyu, et al.
Pubblicazione: (2026)

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

Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing
di: Qi, Leyi, et al.
Pubblicazione: (2026)

Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models
di: Xu, Jingyao, et al.
Pubblicazione: (2024)

Position: Certified Robustness Does Not (Yet) Imply Model Security
di: Cullen, Andrew C., et al.
Pubblicazione: (2025)

CGCE: Classifier-Guided Concept Erasure in Generative Models
di: Nguyen, Viet, et al.
Pubblicazione: (2025)

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

DiffBreak: Is Diffusion-Based Purification Robust?
di: Kassis, Andre, et al.
Pubblicazione: (2024)

QUIC-Fuzz: An Effective Greybox Fuzzer For The QUIC Protocol
di: Ang, Kian Kai, et al.
Pubblicazione: (2025)

Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash
di: Struppek, Lukas, et al.
Pubblicazione: (2021)

Untargeted Near-collision Attacks on Biometrics: Real-world Bounds and Theoretical Limits
di: Durbet, Axel, et al.
Pubblicazione: (2023)

Accuracy Limits as a Barrier to Biometric System Security
di: Durbet, Axel, et al.
Pubblicazione: (2024)

Exploit the Leak: Understanding Risks in Biometric Matchers
di: Durbet, Axel, et al.
Pubblicazione: (2023)

Gradient-based facial encoding for key generation to encrypt and decrypt multimedia data
di: Patel, Ankit Kumar, et al.
Pubblicazione: (2024)

Breaking Semantic-Aware Watermarks via LLM-Guided Coherence-Preserving Semantic Injection
di: Gao, Zheng, et al.
Pubblicazione: (2026)