Search Results for author: Varun Chandrasekaran

Found 25 papers, 11 papers with code

Bypassing LLM Watermarks with Color-Aware Substitutions

no code implementations19 Mar 2024 Qilong Wu, Varun Chandrasekaran

SCTS obtains color information by strategically prompting the watermarked LLM and comparing output tokens frequencies.

Language Modelling Large Language Model

Designing Informative Metrics for Few-Shot Example Selection

no code implementations6 Mar 2024 Rishabh Adiga, Lakshminarayanan Subramanian, Varun Chandrasekaran

This approach avoids the training of a dedicated model for selection of examples, and instead uses certain metrics to align the syntactico-semantic complexity of test sentences and examples.

Few-Shot Learning few-shot-ner +3

Privately Aligning Language Models with Reinforcement Learning

no code implementations25 Oct 2023 Fan Wu, Huseyin A. Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan Kulkarni, Robert Sim

Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training instruction following-models such as ChatGPT.

Instruction Following Privacy Preserving +3

KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval

1 code implementation24 Oct 2023 Marah I Abdin, Suriya Gunasekar, Varun Chandrasekaran, Jerry Li, Mert Yuksekgonul, Rahee Ghosh Peshawaria, Ranjita Naik, Besmira Nushi

Motivated by rising concerns around factual incorrectness and hallucinations of LLMs, we present KITAB, a new dataset for measuring constraint satisfaction abilities of language models.

Information Retrieval Retrieval

Why Train More? Effective and Efficient Membership Inference via Memorization

no code implementations12 Oct 2023 Jihye Choi, Shruti Tople, Varun Chandrasekaran, Somesh Jha

Many practical black-box MIAs require query access to the data distribution (the same distribution where the private data is drawn) to train shadow models.


Diversity of Thought Improves Reasoning Abilities of LLMs

no code implementations11 Oct 2023 Ranjita Naik, Varun Chandrasekaran, Mert Yuksekgonul, Hamid Palangi, Besmira Nushi

Large language models (LLMs) are documented to struggle in settings that require complex reasoning.

Teaching Language Models to Hallucinate Less with Synthetic Tasks

no code implementations10 Oct 2023 Erik Jones, Hamid Palangi, Clarisse Simões, Varun Chandrasekaran, Subhabrata Mukherjee, Arindam Mitra, Ahmed Awadallah, Ece Kamar

We also find that optimizing the system message rather than the model weights can be critical; fine-tuning the entire model on the synthetic task can counterintuitively increase hallucination.

Abstractive Text Summarization Hallucination +3

Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models

1 code implementation26 Sep 2023 Mert Yuksekgonul, Varun Chandrasekaran, Erik Jones, Suriya Gunasekar, Ranjita Naik, Hamid Palangi, Ece Kamar, Besmira Nushi

We investigate the internal behavior of Transformer-based Large Language Models (LLMs) when they generate factually incorrect text.

Sparks of Artificial General Intelligence: Early experiments with GPT-4

2 code implementations22 Mar 2023 Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, Harsha Nori, Hamid Palangi, Marco Tulio Ribeiro, Yi Zhang

We contend that (this early version of) GPT-4 is part of a new cohort of LLMs (along with ChatGPT and Google's PaLM for example) that exhibit more general intelligence than previous AI models.

Arithmetic Reasoning Math Word Problem Solving

Proof-of-Learning is Currently More Broken Than You Think

no code implementations6 Aug 2022 Congyu Fang, Hengrui Jia, Anvith Thudi, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Varun Chandrasekaran, Nicolas Papernot

They empirically argued the benefit of this approach by showing how spoofing--computing a proof for a stolen model--is as expensive as obtaining the proof honestly by training the model.

Learning Theory

Hierarchical Federated Learning with Privacy

no code implementations10 Jun 2022 Varun Chandrasekaran, Suman Banerjee, Diego Perino, Nicolas Kourtellis

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.

Federated Learning

SoK: Machine Learning Governance

no code implementations20 Sep 2021 Varun Chandrasekaran, Hengrui Jia, Anvith Thudi, Adelin Travers, Mohammad Yaghini, Nicolas Papernot

The application of machine learning (ML) in computer systems introduces not only many benefits but also risks to society.

BIG-bench Machine Learning

Proof-of-Learning: Definitions and Practice

2 code implementations9 Mar 2021 Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Anvith Thudi, Varun Chandrasekaran, Nicolas Papernot

In particular, our analyses and experiments show that an adversary seeking to illegitimately manufacture a proof-of-learning needs to perform *at least* as much work than is needed for gradient descent itself.

A General Framework For Detecting Anomalous Inputs to DNN Classifiers

1 code implementation29 Jul 2020 Jayaram Raghuram, Varun Chandrasekaran, Somesh Jha, Suman Banerjee

We propose an unsupervised anomaly detection framework based on the internal DNN layer representations in the form of a meta-algorithm with configurable components.

Image Classification Unsupervised Anomaly Detection

Face-Off: Adversarial Face Obfuscation

1 code implementation19 Mar 2020 Chuhan Gao, Varun Chandrasekaran, Kassem Fawaz, Somesh Jha

We implement and evaluate Face-Off to find that it deceives three commercial face recognition services from Microsoft, Amazon, and Face++.

Cryptography and Security

Entangled Watermarks as a Defense against Model Extraction

3 code implementations27 Feb 2020 Hengrui Jia, Christopher A. Choquette-Choo, Varun Chandrasekaran, Nicolas Papernot

Such pairs are watermarks, which are not sampled from the task distribution and are only known to the defender.

Model extraction Transfer Learning

On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping

1 code implementation26 Feb 2020 Sanghyun Hong, Varun Chandrasekaran, Yiğitcan Kaya, Tudor Dumitraş, Nicolas Papernot

In this work, we study the feasibility of an attack-agnostic defense relying on artifacts that are common to all poisoning attacks.

Data Poisoning

Machine Unlearning

2 code implementations9 Dec 2019 Lucas Bourtoule, Varun Chandrasekaran, Christopher A. Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, Nicolas Papernot

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 Unlearning Transfer Learning

Generating Semantic Adversarial Examples with Differentiable Rendering

no code implementations2 Oct 2019 Lakshya Jain, Wilson Wu, Steven Chen, Uyeong Jang, Varun Chandrasekaran, Sanjit Seshia, Somesh Jha

In this paper we explore semantic adversarial examples (SAEs) where an attacker creates perturbations in the semantic space representing the environment that produces input for the ML model.

Autonomous Driving

Rearchitecting Classification Frameworks For Increased Robustness

no code implementations26 May 2019 Varun Chandrasekaran, Brian Tang, Nicolas Papernot, Kassem Fawaz, Somesh Jha, Xi Wu

and how to design a classification paradigm that leverages these invariances to improve the robustness accuracy trade-off?

Autonomous Driving Classification +2

Exploring Connections Between Active Learning and Model Extraction

no code implementations5 Nov 2018 Varun Chandrasekaran, Kamalika Chaudhuri, Irene Giacomelli, Somesh Jha, Songbai Yan

This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud services that provide (a) tools and resources to learn the model, and (b) a user-friendly query interface to access the model.

Active Learning BIG-bench Machine Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.