Imagen de Portada

Buffer Overflow in Mixture of Experts

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hayes, Jamie, Shumailov, Ilia, Yona, Itay
Formato:	Preprint
Publicado:	2024
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

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

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

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

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

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

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

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)

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

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

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

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

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

Locking Machine Learning Models into Hardware
por: Clifford, Eleanor, et al.
Publicado: (2024)

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

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

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

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

When Vision Fails: Text Attacks Against ViT and OCR
por: Boucher, Nicholas, et al.
Publicado: (2023)

Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots
por: Vero, Mark, et al.
Publicado: (2026)

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

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

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

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

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

In-Context Representation Hijacking
por: Yona, Itay, et al.
Publicado: (2025)

Tighter Risk Bounds for Mixtures of Experts
por: Akretche, Wissam, et al.
Publicado: (2024)

Differentially Private Training of Mixture of Experts Models
por: Tholoniat, Pierre, et al.
Publicado: (2024)

Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense
por: Han, Qiao, et al.
Publicado: (2024)

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

MERLOT: A Distilled LLM-based Mixture-of-Experts Framework for Scalable Encrypted Traffic Classification
por: Chen, Yuxuan, et al.
Publicado: (2024)

Provable Privacy Attacks on Trained Shallow Neural Networks
por: Smorodinsky, Guy, et al.
Publicado: (2024)

To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling
por: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Publicado: (2024)

Defending Buffer Overflows in WebAssembly: A Transpiler Approach
por: Feng, Weiqi
Publicado: (2026)

The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing
por: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Publicado: (2025)

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

RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models
por: Liang, Jiacheng, et al.
Publicado: (2026)

Exploring the limits of strong membership inference attacks on large language models
por: Hayes, Jamie, et al.
Publicado: (2025)

Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs
por: Jiang, Yukun, et al.
Publicado: (2026)

PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning
por: Feng, Yu, et al.
Publicado: (2025)