17 citations · 21 across the 14 of their papers we have counts for
15 papers
Muse Glimmer 30B: An On-Device Agentic Model
Arash Ebrahim Abtahizadeh, Muna Aghamelu, Adil Ahmed +327
We introduce Muse Glimmer, an open-source 30B parameter causal language model with perception encoder, purpose-built for autonomous agentic tasks on consumer hardware. Muse Glimmer…
Inadvertent Context Leakage in Language Models
Jaiden Fairoze, Neal Mangaokar, Kamalika Chaudhuri +2
For AI agents to be useful beyond simple chat, they must hold sensitive user context such as calendars, credentials, health records, and financial data. We study whether the mere p…
Learning to Reason in 13 Parameters
John X. Morris, Niloofar Mireshghallah, Mark Ibrahim +1
Recent research has shown that language models can learn to \textit{reason}, often via reinforcement learning. Some work even trains low-rank parameterizations for reasoning, but c…
Privacy Blur: Quantifying Privacy and Utility for Image Data Release
Saeed Mahloujifar, Narine Kokhlikyan, Chuan Guo +1
Image data collected in the wild often contains private information such as faces and license plates, and responsible data release must ensure that this information stays hidden. A…
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…
Observational Auditing of Label Privacy
Iden Kalemaj, Luca Melis, Maxime Boucher +2
Differential privacy (DP) auditing is essential for evaluating privacy guarantees in machine learning systems. Existing auditing methods, however, pose a significant challenge for…
Z0-Inf: Zeroth Order Approximation for Data Influence
Narine Kokhlikyan, Kamalika Chaudhuri, Saeed Mahloujifar
A critical aspect of analyzing and improving modern machine learning systems lies in understanding how individual training examples influence a model's predictive behavior. Estimat…
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…
How much do language models memorize?
John X. Morris, Chawin Sitawarin, Chuan Guo +5
We propose a new method for estimating how much a model knows about a datapoint and use it to measure the capacity of modern language models. Prior studies of language model memori…
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…
Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstruction
Sai Qian Zhang, Ziyun Li, Chuan Guo +5
Inverting visual representations within deep neural networks (DNNs) presents a challenging and important problem in the field of security and privacy for deep learning. The main go…
Auditing -Differential Privacy in One Run
Saeed Mahloujifar, Luca Melis, Kamalika Chaudhuri
Empirical auditing has emerged as a means of catching some of the flaws in the implementation of privacy-preserving algorithms. Existing auditing mechanisms, however, are either co…
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…
Guarantees of confidentiality via Hammersley-Chapman-Robbins bounds
Kamalika Chaudhuri, Chuan Guo, Laurens van der Maaten +2
Protecting privacy during inference with deep neural networks is possible by adding noise to the activations in the last layers prior to the final classifiers or other task-specifi…
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…