Cover Image

Stealing User Prompts from Mixture of Experts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yona, Itay, Shumailov, Ilia, Hayes, Jamie, Carlini, Nicholas
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

In-Context Representation Hijacking
by: Yona, Itay, et al.
Published: (2025)

Query-Based Adversarial Prompt Generation
by: Hayase, Jonathan, et al.
Published: (2024)

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

Teach LLMs to Phish: Stealing Private Information from Language Models
by: Panda, Ashwinee, et al.
Published: (2024)

Defeating Prompt Injections by Design
by: Debenedetti, Edoardo, et al.
Published: (2025)

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

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

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

MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification
by: Jiang, Weisen, et al.
Published: (2026)

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

Watermarking Needs Input Repetition Masking
by: Khachaturov, David, et al.
Published: (2025)

AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models
by: Reddy, Aashray, et al.
Published: (2025)

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

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

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

Are aligned neural networks adversarially aligned?
by: Carlini, Nicholas, et al.
Published: (2023)

PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization
by: Geng, Runpeng, et al.
Published: (2025)

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

Jailbreaking with Universal Multi-Prompts
by: Hsu, Yu-Ling, et al.
Published: (2025)

You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors
by: Cao, Bochuan, et al.
Published: (2025)

SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains
by: Saiem, Bijoy Ahmed, et al.
Published: (2024)

PIArena: A Platform for Prompt Injection Evaluation
by: Geng, Runpeng, et al.
Published: (2026)

Certifying LLM Safety against Adversarial Prompting
by: Kumar, Aounon, et al.
Published: (2023)

Formalizing and Benchmarking Prompt Injection Attacks and Defenses
by: Liu, Yupei, et al.
Published: (2023)

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

MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks
by: Cornacchia, Giandomenico, et al.
Published: (2024)

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
by: Paulus, Anselm, et al.
Published: (2024)

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

Fight Back Against Jailbreaking via Prompt Adversarial Tuning
by: Mo, Yichuan, et al.
Published: (2024)

Systematically Analyzing Prompt Injection Vulnerabilities in Diverse LLM Architectures
by: Benjamin, Victoria, et al.
Published: (2024)

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
by: Shao, Zedian, et al.
Published: (2024)

Unlocking Memorization in Large Language Models with Dynamic Soft Prompting
by: Wang, Zhepeng, et al.
Published: (2024)

TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification
by: Gubri, Martin, et al.
Published: (2024)

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

Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
by: Zhao, Andrew, et al.
Published: (2025)