conference paper

Rerouting LLM Routers

LLM routers aim to balance quality and cost of generation by classifying queries and routing them to a cheaper or more expensive LLM …

Avital Shafran, Roei Schuster, Thomas Ristenpart, Vitaly Shmatikov
PDF Cite
Beyond Labeling Oracles: What does it mean to steal ML models?
Model extraction attacks are designed to steal trained models with only query access, as is often provided through APIs that …
Avital Shafran, Ilia Shumailov, Murat A. Erdogdu, Nicolas Papernot
PDF Cite
Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents

Retrieval-augmented generation (RAG) systems respond to queries by retrieving relevant documents from a knowledge database, then …

Avital Shafran, Roei Schuster, Vitaly Shmatikov
PDF Cite
Is ML-Based Cryptanalysis Inherently Limited? Simulating Cryptographic Adversaries via Gradient-Based Methods

Given the recent progress in machine learning (ML), the cryptography community has started exploring the applicability of ML methods to …

Avital Shafran, Eran Malach, Thomas Ristenpart, Gil Segev, Stefano Tessaro
PDF Cite
Membership inference attacks are easier on difficult problems
Membership inference attacks (MIA) try to detect if data samples were used to train a neural network model, e.g. to detect copyright …
Avital Shafran, Shmuel Peleg, Yedid Hoshen
PDF Cite
Crypto-Oriented Neural Architecture Design
Sending private data to Neural Network applications raises many privacy concerns. The cryptography community developed a variety of …
Avital Shafran, Gil Segev, Shmuel Peleg, Yedid Hoshen
PDF Cite