1.6k citations · 1.7k across the 22 of their papers we have counts for
23 papers
Challenges in Enabling Private Data Valuation
Yiwei Fu, Tianhao Wang, Varun Chandrasekaran
Data valuation methods quantify how individual training examples contribute to a model's behavior, and are increasingly used for dataset curation, auditing, and emerging data marke…
SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification
Tianyang Zhou, Ziyi Zhang, Haowen Lin +4
Translating software written in C to Rust has significant benefits in improving memory safety. However, manual translation is cumbersome, error-prone, and often produces unidiomati…
Why Train More? Effective and Efficient Membership Inference via Memorization
Jihye Choi, Shruti Tople, Varun Chandrasekaran +1
Membership Inference Attacks (MIAs) aim to identify specific data samples within the private training dataset of machine learning models, leading to serious privacy violations and…
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan +11
Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks,…
Verifiable and Provably Secure Machine Unlearning
Thorsten Eisenhofer, Doreen Riepel, Varun Chandrasekaran +3
Machine unlearning aims to remove points from the training dataset of a machine learning model after training: e.g., when a user requests their data to be deleted. While many unlea…
Proof-of-Learning is Currently More Broken Than You Think
Congyu Fang, Hengrui Jia, Anvith Thudi +5
Proof-of-Learning (PoL) proposes that a model owner logs training checkpoints to establish a proof of having expended the computation necessary for training. The authors of PoL for…
Generative Extraction of Audio Classifiers for Speaker Identification
Tejumade Afonja, Lucas Bourtoule, Varun Chandrasekaran +2
It is perhaps no longer surprising that machine learning models, especially deep neural networks, are particularly vulnerable to attacks. One such vulnerability that has been well…
Hierarchical Federated Learning with Privacy
Varun Chandrasekaran, Suman Banerjee, Diego Perino +1
Federated learning (FL), where data remains at the federated clients, and where only gradient updates are shared with a central aggregator, was assumed to be private. Recent work d…
CONFIDANT: A Privacy Controller for Social Robots
Brian Tang, Dakota Sullivan, Bengisu Cagiltay +3
As social robots become increasingly prevalent in day-to-day environments, they will participate in conversations and appropriately manage the information shared with them. However…
SoK: Machine Learning Governance
Varun Chandrasekaran, Hengrui Jia, Anvith Thudi +3
The application of machine learning (ML) in computer systems introduces not only many benefits but also risks to society. In this paper, we develop the concept of ML governance to…
Unrolling SGD: Understanding Factors Influencing Machine Unlearning
Anvith Thudi, Gabriel Deza, Varun Chandrasekaran +1
Machine unlearning is the process through which a deployed machine learning model is made to forget about some of its training data points. While naively retraining the model from…
On the Exploitability of Audio Machine Learning Pipelines to Surreptitious Adversarial Examples
Adelin Travers, Lorna Licollari, Guanghan Wang +4
Machine learning (ML) models are known to be vulnerable to adversarial examples. Applications of ML to voice biometrics authentication are no exception. Yet, the implications of au…
Causally Constrained Data Synthesis for Private Data Release
Varun Chandrasekaran, Darren Edge, Somesh Jha +3
Making evidence based decisions requires data. However for real-world applications, the privacy of data is critical. Using synthetic data which reflects certain statistical propert…
Proof-of-Learning: Definitions and Practice
Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo +4
Training machine learning (ML) models typically involves expensive iterative optimization. Once the model's final parameters are released, there is currently no mechanism for the e…
A General Framework For Detecting Anomalous Inputs to DNN Classifiers
Jayaram Raghuram, Varun Chandrasekaran, Somesh Jha +1
Detecting anomalous inputs, such as adversarial and out-of-distribution (OOD) inputs, is critical for classifiers (including deep neural networks or DNNs) deployed in real-world ap…
Face-Off: Adversarial Face Obfuscation
Varun Chandrasekaran, Chuhan Gao, Brian Tang +3
Advances in deep learning have made face recognition technologies pervasive. While useful to social media platforms and users, this technology carries significant privacy threats.…
On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping
Sanghyun Hong, Varun Chandrasekaran, Yiğitcan Kaya +2
Machine learning algorithms are vulnerable to data poisoning attacks. Prior taxonomies that focus on specific scenarios, e.g., indiscriminate or targeted, have enabled defenses for…
Machine Unlearning
Lucas Bourtoule, Varun Chandrasekaran, Christopher A. Choquette-Choo +5
Once users have shared their data online, it is generally difficult for them to revoke access and ask for the data to be deleted. Machine learning (ML) exacerbates this problem bec…
Analyzing and Improving Neural Networks by Generating Semantic Counterexamples through Differentiable Rendering
Lakshya Jain, Varun Chandrasekaran, Uyeong Jang +6
Even as deep neural networks (DNNs) have achieved remarkable success on vision-related tasks, their performance is brittle to transformations in the input. Of particular interest a…
Rearchitecting Classification Frameworks For Increased Robustness
Varun Chandrasekaran, Brian Tang, Nicolas Papernot +3
While generalizing well over natural inputs, neural networks are vulnerable to adversarial inputs. Existing defenses against adversarial inputs have largely been detached from the…
PowerCut and Obfuscator: An Exploration of the Design Space for Privacy-Preserving Interventions for Voice Assistants
Varun Chandrasekaran, Suman Banerjee, Bilge Mutlu +1
The pervasive use of smart speakers has raised numerous privacy concerns. While work to date provides an understanding of user perceptions of these threats, limited research focuse…
Exploring Connections Between Active Learning and Model Extraction
Varun Chandrasekaran, Kamalika Chaudhuri, Irene Giacomelli +2
Machine learning is being increasingly used by individuals, research institutions, and corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud…
Secure Mobile Identities
Varun Chandrasekaran, Fareeha Amjad, Ashlesh Sharma +1
The unique identities of every mobile user (phone number,IMSI) and device (IMEI) are far from secure and are increasingly vulnerable to a variety of network-level threats. The exce…