70 citations · 293 across the 70 of their papers we have counts for
73 papers
Feedback Coding Enables Inference-Time Covert Agentic Communication
Sidong Guo, Sajani Vithana, Atefeh Gilani +3
As large language models (LLMs) are increasingly used to automate digital interactions, users can leverage LLM-generated text as cover for covert communication within seemingly ben…
A Complete Characterization of Tensorizable -divergences
Rodrigo Cruz, Flavio P. Calmon, Qian Yu
Csiszar's formulation of the -divergence introduced a vast family of functionals for quantifying dissimilarity between probability distributions. However, many applications in s…
Optimal Domain-Aware Privacy Mechanisms for Synthetic Data Generation
Sajani Vithana, Sangwon Jung, Haoyang Hu +3
Differential privacy (DP) imposes fundamental trade-offs between privacy and statistical fidelity in synthetic data generation. While access to public data has been shown to improv…
Sort, Partition, Randomize: Optimal Binary Hypothesis Testing under Local Differential Privacy
Elena Ghazi, Jawad Nasser, Flavio Calmon +1
We study optimal design of -locally differentially private mechanisms for binary hypothesis testing. Each observation is drawn from one of two known distributions $P_0…
ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport
Atefeh Gilani, Sajani Vithana, Carol Xuan Long +3
Watermarking is an important tool for promoting the responsible use of large language models (LLMs). Existing watermarks insert a signal into generated tokens that either flags LLM…
RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories
Roy Rinberg, Usha Bhalla, Igor Shilov +2
Targeted interventions on language models, such as unlearning or model editing, aim to modify specific information, but their effects often propagate to related, unintended areas (…
Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability
Usha Bhalla, Alex Oesterling, Claudio Mayrink Verdun +2
Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning met…
An information theorist's tour of differential privacy
Anand D. Sarwate, Flavio P. Calmon, Oliver Kosut +1
Since being proposed in 2006, differential privacy has become a standard method for quantifying certain risks in publishing or sharing analyses of sensitive data. At its heart, dif…
HeavyWater and SimplexWater: Distortion-Free LLM Watermarks for Low-Entropy Next-Token Predictions
Dor Tsur, Carol Xuan Long, Claudio Mayrink Verdun +5
Large language model (LLM) watermarks enable authentication of text provenance, curb misuse of machine-generated text, and promote trust in AI systems. Current watermarks operate b…
Multi-Group Proportional Representation for Text-to-Image Models
Sangwon Jung, Alex Oesterling, Claudio Mayrink Verdun +3
Text-to-image (T2I) generative models can create vivid, realistic images from textual descriptions. As these models proliferate, they expose new concerns about their ability to rep…
Optimized Couplings for Watermarking Large Language Models
Dor Tsur, Carol Xuan Long, Claudio Mayrink Verdun +3
Large-language models (LLMs) are now able to produce text that is, in many cases, seemingly indistinguishable from human-generated content. This has fueled the development of water…
Soft Best-of-n Sampling for Model Alignment
Claudio Mayrink Verdun, Alex Oesterling, Himabindu Lakkaraju +1
Best-of- (BoN) sampling is a practical approach for aligning language model outputs with human preferences without expensive fine-tuning. BoN sampling is performed by generating…
Optimizing Noise Distributions for Differential Privacy
Atefeh Gilani, Juan Felipe Gomez, Shahab Asoodeh +3
We propose a unified optimization framework for designing continuous and discrete noise distributions that ensure differential privacy (DP) by minimizing Rényi DP, a variant of DP,…
Regretful Decisions under Label Noise
Sujay Nagaraj, Yang Liu, Flavio P. Calmon +1
Machine learning models are routinely used to support decisions that affect individuals -- be it to screen a patient for a serious illness or to gauge their response to treatment.…
Multi-Group Proportional Representation in Retrieval
Alex Oesterling, Claudio Mayrink Verdun, Carol Xuan Long +5
Image search and retrieval tasks can perpetuate harmful stereotypes, erase cultural identities, and amplify social disparities. Current approaches to mitigate these representationa…
Correlated Privacy Mechanisms for Differentially Private Distributed Mean Estimation
Sajani Vithana, Viveck R. Cadambe, Flavio P. Calmon +1
Differentially private distributed mean estimation (DP-DME) is a fundamental building block in privacy-preserving federated learning, where a central server estimates the mean of $…
Selective Explanations
Lucas Monteiro Paes, Dennis Wei, Flavio P. Calmon
Feature attribution methods explain black-box machine learning (ML) models by assigning importance scores to input features. These methods can be computationally expensive for larg…
Algorithmic Arbitrariness in Content Moderation
Juan Felipe Gomez, Caio Vieira Machado, Lucas Monteiro Paes +1
Machine learning (ML) is widely used to moderate online content. Despite its scalability relative to human moderation, the use of ML introduces unique challenges to content moderat…
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
Usha Bhalla, Alex Oesterling, Suraj Srinivas +2
CLIP embeddings have demonstrated remarkable performance across a wide range of multimodal applications. However, these high-dimensional, dense vector representations are not easil…
Multi-Group Fairness Evaluation via Conditional Value-at-Risk Testing
Lucas Monteiro Paes, Ananda Theertha Suresh, Alex Beutel +2
Machine learning (ML) models used in prediction and classification tasks may display performance disparities across population groups determined by sensitive attributes (e.g., race…
Differentially Private Secure Multiplication: Hiding Information in the Rubble of Noise
Viveck R. Cadambe, Ateet Devulapalli, Haewon Jeong +1
We consider the problem of private distributed multi-party multiplication. It is well-established that Shamir secret-sharing coding strategies can enable perfect information-theore…
Fair Machine Unlearning: Data Removal while Mitigating Disparities
Alex Oesterling, Jiaqi Ma, Flavio P. Calmon +1
The Right to be Forgotten is a core principle outlined by regulatory frameworks such as the EU's General Data Protection Regulation (GDPR). This principle allows individuals to req…
Arbitrariness Lies Beyond the Fairness-Accuracy Frontier
Carol Xuan Long, Hsiang Hsu, Wael Alghamdi +1
Machine learning tasks may admit multiple competing models that achieve similar performance yet produce conflicting outputs for individual samples -- a phenomenon known as predicti…
Adapting Fairness Interventions to Missing Values
Raymond Feng, Flavio P. Calmon, Hao Wang
Missing values in real-world data pose a significant and unique challenge to algorithmic fairness. Different demographic groups may be unequally affected by missing data, and the s…