9 citations · 14 across the 14 of their papers we have counts for
15 papers
SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents
Rui Melo, Riccardo Fogliato, Sean Zhou +2
Large language models (LLMs) are increasingly deployed in automated code-review systems, where their approvals can determine which code is merged into shared repositories. However,…
Personalization, Personas, and Forecasting in Value Alignment
James Wedgwood, Pratiksha Thaker, Neil Kale +1
LLM behavior may be conditioned by human identity in several ways: they may be asked to adapt to users, role-play populations, or forecast how people would answer value-laden quest…
Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety
Neil Kale, Rebecca Portnoff, Pratiksha Thaker +5
Modern artificial intelligence (AI) systems present profound new risks to child safety. AI is increasingly being misused to create AI-generated child sexual abuse material, facilit…
Lower Bounds for Public-Private Learning under Distribution Shift
Amrith Setlur, Pratiksha Thaker, Jonathan Ullman
The most effective differentially private machine learning algorithms in practice rely on an additional source of purportedly public data. This paradigm is most interesting when th…
Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership Inference
Terrance Liu, Matteo Boglioni, Yiwei Fu +3
Differential privacy (DP) auditing aims to provide empirical lower bounds on the privacy guarantees of DP mechanisms like DP-SGD. While some existing techniques require many traini…
PARALLELPROMPT: Extracting Parallelism from Large Language Model Queries
Steven Kolawole, Keshav Santhanam, Virginia Smith +1
LLM serving systems typically treat user prompts as monolithic inputs, optimizing inference through decoding tricks or inter-query batching. However, many real-world prompts contai…
Membership Inference Attacks for Unseen Classes
Pratiksha Thaker, Neil Kale, Zhiwei Steven Wu +1
A key tool in developing safe AI models is \emph{data auditing}, i.e., using statistical tools to determine whether harmful content may have been used in the training data of a bla…
BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap
Shengyuan Hu, Neil Kale, Pratiksha Thaker +3
Machine unlearning has the potential to improve the safety of large language models (LLMs) by removing sensitive or harmful information post hoc. A key challenge in unlearning invo…
Generate-then-Verify: Reconstructing Data from Limited Published Statistics
Terrance Liu, Eileen Xiao, Adam Smith +2
We study the problem of reconstructing tabular data from aggregate statistics, in which the attacker aims to identify interesting claims about the sensitive data that can be verifi…
Position: LLM Unlearning Benchmarks are Weak Measures of Progress
Pratiksha Thaker, Shengyuan Hu, Neil Kale +3
Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning re…
Alto: Orchestrating Distributed Compound AI Systems with Nested Ancestry
Deepti Raghavan, Keshav Santhanam, Muhammad Shahir Rahman +7
Compound AI applications chain together subcomponents such as generative language models, document retrievers, and embedding models. Applying traditional systems optimizations such…
Guardrail Baselines for Unlearning in LLMs
Pratiksha Thaker, Yash Maurya, Shengyuan Hu +2
Recent work has demonstrated that finetuning is a promising approach to 'unlearn' concepts from large language models. However, finetuning can be expensive, as it requires both gen…
On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
Pratiksha Thaker, Amrith Setlur, Zhiwei Steven Wu +1
Public pretraining is a promising approach to improve differentially private model training. However, recent work has noted that many positive research results studying this paradi…
On Noisy Evaluation in Federated Hyperparameter Tuning
Kevin Kuo, Pratiksha Thaker, Mikhail Khodak +4
Hyperparameter tuning is critical to the success of federated learning applications. Unfortunately, appropriately selecting hyperparameters is challenging in federated networks. Is…
Overlook: Differentially Private Exploratory Visualization for Big Data
Pratiksha Thaker, Mihai Budiu, Parikshit Gopalan +2
Data exploration systems that provide differential privacy must manage a privacy budget that measures the amount of privacy lost across multiple queries. One effective strategy to…