Imagen de Portada

When Vision Fails: Text Attacks Against ViT and OCR

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Boucher, Nicholas, Blessing, Jenny, Shumailov, Ilia, Anderson, Ross, Papernot, Nicolas
Formato:	Preprint
Publicado:	2023
Materias:	Cryptography and Security Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beyond Labeling Oracles: What does it mean to steal ML models?
por: Shafran, Avital, et al.
Publicado: (2023)

Beyond Laplace and Gaussian: Exploring the Generalized Gaussian Mechanism for Private Machine Learning
por: Rinberg, Roy, et al.
Publicado: (2025)

Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
por: Hayes, Jamie, et al.
Publicado: (2024)

Machine Learning needs Better Randomness Standards: Randomised Smoothing and PRNG-based attacks
por: Dahiya, Pranav, et al.
Publicado: (2023)

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
por: Thudi, Anvith, et al.
Publicado: (2023)

SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks
por: Gao, Yue, et al.
Publicado: (2023)

ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks
por: Clifford, Eleanor, et al.
Publicado: (2022)

The Curse of Recursion: Training on Generated Data Makes Models Forget
por: Shumailov, Ilia, et al.
Publicado: (2023)

Architectural Neural Backdoors from First Principles
por: Langford, Harry, et al.
Publicado: (2024)

Buffer Overflow in Mixture of Experts
por: Hayes, Jamie, et al.
Publicado: (2024)

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
por: Nasr, Milad, et al.
Publicado: (2025)

Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation
por: Küchler, Nicolas, et al.
Publicado: (2025)

ceLLMate: Sandboxing Browser AI Agents
por: Meng, Luoxi, et al.
Publicado: (2025)

Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models
por: Chaudhari, Harsh, et al.
Publicado: (2026)

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
por: Cebere, Tudor, et al.
Publicado: (2024)

Stealing User Prompts from Mixture of Experts
por: Yona, Itay, et al.
Publicado: (2024)

Soft Instruction De-escalation Defense
por: Walter, Nils Philipp, et al.
Publicado: (2025)

Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated
por: Foerster, Hanna, et al.
Publicado: (2025)

Watermarking Needs Input Repetition Masking
por: Khachaturov, David, et al.
Publicado: (2025)

Beyond Slow Signs in High-fidelity Model Extraction
por: Foerster, Hanna, et al.
Publicado: (2024)

UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
por: Shumailov, Ilia, et al.
Publicado: (2024)

Machine Learning Models Have a Supply Chain Problem
por: Meiklejohn, Sarah, et al.
Publicado: (2025)

Cascading Adversarial Bias from Injection to Distillation in Language Models
por: Chaudhari, Harsh, et al.
Publicado: (2025)

Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
por: Foerster, Hanna, et al.
Publicado: (2026)

Prompt Stealing Attacks Against Text-to-Image Generation Models
por: Shen, Xinyue, et al.
Publicado: (2023)

Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses
por: Glukhov, David, et al.
Publicado: (2024)

Lessons from Defending Gemini Against Indirect Prompt Injections
por: Shi, Chongyang, et al.
Publicado: (2025)

On the Privacy Risk of In-context Learning
por: Duan, Haonan, et al.
Publicado: (2024)

Private Rate-Constrained Optimization with Applications to Fair Learning
por: Yaghini, Mohammad, et al.
Publicado: (2025)

The Fundamental Limits of Least-Privilege Learning
por: Stadler, Theresa, et al.
Publicado: (2024)

Learned-Database Systems Security
por: Schuster, Roei, et al.
Publicado: (2022)

LLM Dataset Inference: Did you train on my dataset?
por: Maini, Pratyush, et al.
Publicado: (2024)

Efficient Public Verification of Private ML via Regularization
por: Bell, Zoë Ruha, et al.
Publicado: (2025)

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

Instruction Backdoor Attacks Against Customized LLMs
por: Zhang, Rui, et al.
Publicado: (2024)

ViT Enhanced Privacy-Preserving Secure Medical Data Sharing and Classification
por: Amin, Al, et al.
Publicado: (2024)

Interpreting the Repeated Token Phenomenon in Large Language Models
por: Yona, Itay, et al.
Publicado: (2025)

Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography
por: Shumailov, Ilia, et al.
Publicado: (2025)

Pr$εε$mpt: Sanitizing Sensitive Prompts for LLMs
por: Chowdhury, Amrita Roy, et al.
Publicado: (2025)

KeyDroid: A Large-Scale Analysis of Secure Key Storage in Android Apps
por: Blessing, Jenny, et al.
Publicado: (2025)