88 citations · 91 across the 9 of their papers we have counts for
5 papers · 1 filter
Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models
Harsh Chaudhari, Ethan Rathbun, Hanna Foerster +5
Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks.…
Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated
Hanna Foerster, Ilia Shumailov, Yiren Zhao +4
Early research into data poisoning attacks against Large Language Models (LLMs) demonstrated the ease with which backdoors could be injected. More recent LLMs add step-by-step reas…
Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
Ali Naseh, Yuefeng Peng, Anshuman Suri +3
Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to generate grounded responses by leveraging external knowledge databases without altering model parameter…
UTrace: Poisoning Forensics for Private Collaborative Learning
Evan Rose, Hidde Lycklama, Harsh Chaudhari +3
Privacy-preserving machine learning (PPML) systems enable multiple data owners to collaboratively train models without revealing their raw, sensitive data by leveraging cryptograph…
ASTRA: High Throughput 3PC over Rings with Application to Secure Prediction
Harsh Chaudhari, Ashish Choudhury, Arpita Patra +1
The concrete efficiency of secure computation has been the focus of many recent works. In this work, we present concretely-efficient protocols for secure -party computation (3PC…