17 citations · 21 across the 14 of their papers we have counts for
5 papers · 1 filter
CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs
Niloofar Mireshghallah, Neal Mangaokar, Narine Kokhlikyan +4
Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory introduces critical ris…
Machine Learning with Privacy for Protected Attributes
Saeed Mahloujifar, Chuan Guo, G. Edward Suh +1
Differential privacy (DP) has become the standard for private data analysis. Certain machine learning applications only require privacy protection for specific protected attributes…
Detecting Benchmark Contamination Through Watermarking
Tom Sander, Pierre Fernandez, Saeed Mahloujifar +2
Benchmark contamination poses a significant challenge to the reliability of Large Language Models (LLMs) evaluations, as it is difficult to assert whether a model has been trained…
SecAlign: Defending Against Prompt Injection with Preference Optimization
Sizhe Chen, Arman Zharmagambetov, Saeed Mahloujifar +3
Large language models (LLMs) are becoming increasingly prevalent in modern software systems, interfacing between the user and the Internet to assist with tasks that require advance…
Privacy Amplification for the Gaussian Mechanism via Bounded Support
Shengyuan Hu, Saeed Mahloujifar, Virginia Smith +2
Data-dependent privacy accounting frameworks such as per-instance differential privacy (pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for individual…