280 citations · 1.4k across the 75 of their papers we have counts for
36 papers · 1 filter
Correlated Noise Mechanisms for Differentially Private Learning
Krishna Pillutla, Jalaj Upadhyay, Christopher A. Choquette-Choo +9
This monograph explores the design and analysis of correlated noise mechanisms for differential privacy (DP), focusing on their application to private training of AI and machine le…
Large Language Models Can Verbatim Reproduce Long Malicious Sequences
Sharon Lin, Krishnamurthy, Dvijotham +4
Backdoor attacks on machine learning models have been extensively studied, primarily within the computer vision domain. Originally, these attacks manipulated classifiers to generat…
Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning
Avinandan Bose, Laurent Lessard, Maryam Fazel +1
The rise of foundation models fine-tuned on human feedback from potentially untrusted users has increased the risk of adversarial data poisoning, necessitating the study of robustn…
Norm-Bounded Low-Rank Adaptation
Ruigang Wang, Krishnamurthy Dvijotham, Ian R. Manchester
In this work, we propose norm-bounded low-rank adaptation (NB-LoRA) for parameter-efficient fine tuning. NB-LoRA is a novel parameterization of low-rank weight adaptations that adm…
BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks
Juan Rodriguez, Xiangru Jian, Siba Smarak Panigrahi +40
Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows, extracting data from documents, and sum…
Achieving the Tightest Relaxation of Sigmoids for Formal Verification
Samuel Chevalier, Duncan Starkenburg, Krishnamurthy Dvijotham
In the field of formal verification, Neural Networks (NNs) are typically reformulated into equivalent mathematical programs which are optimized over. To overcome the inherent non-c…
Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation
Katherine M. Collins, Najoung Kim, Yonatan Bitton +15
Human feedback plays a critical role in learning and refining reward models for text-to-image generation, but the optimal form the feedback should take for learning an accurate rew…
Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
Kyuyoung Kim, Jongheon Jeong, Minyong An +4
Fine-tuning text-to-image models with reward functions trained on human feedback data has proven effective for aligning model behavior with human intent. However, excessive optimiz…
Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
Gavin Brown, Krishnamurthy Dvijotham, Georgina Evans +3
We provide an improved analysis of standard differentially private gradient descent for linear regression under the squared error loss. Under modest assumptions on the input, we ch…
Monotone, Bi-Lipschitz, and Polyak-Lojasiewicz Networks
Ruigang Wang, Krishnamurthy Dvijotham, Ian R. Manchester
This paper presents a new bi-Lipschitz invertible neural network, the BiLipNet, which has the ability to smoothly control both its Lipschitzness (output sensitivity to input pertur…
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
Christopher A. Choquette-Choo, Krishnamurthy Dvijotham, Krishna Pillutla +3
Differentially private learning algorithms inject noise into the learning process. While the most common private learning algorithm, DP-SGD, adds independent Gaussian noise in each…
Learning to Receive Help: Intervention-Aware Concept Embedding Models
Mateo Espinosa Zarlenga, Katherine M. Collins, Krishnamurthy Dvijotham +3
Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by constructing and explaining their predictions using a set of high-level concepts. A special property…
Faithful Knowledge Distillation
Tom A. Lamb, Rudy Brunel, Krishnamurthy DJ Dvijotham +3
Knowledge distillation (KD) has received much attention due to its success in compressing networks to allow for their deployment in resource-constrained systems. While the problem…
Training Private Models That Know What They Don't Know
Stephan Rabanser, Anvith Thudi, Abhradeep Thakurta +2
Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning h…
Expressive Losses for Verified Robustness via Convex Combinations
Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham +3
In order to train networks for verified adversarial robustness, it is common to over-approximate the worst-case loss over perturbation regions, resulting in networks that attain ve…
Efficient Error Certification for Physics-Informed Neural Networks
Francisco Eiras, Adel Bibi, Rudy Bunel +3
Recent work provides promising evidence that Physics-Informed Neural Networks (PINN) can efficiently solve partial differential equations (PDE). However, previous works have failed…
Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play
Jeremiah Zhe Liu, Krishnamurthy Dj Dvijotham, Jihyeon Lee +4
Standard empirical risk minimization (ERM) training can produce deep neural network (DNN) models that are accurate on average but under-perform in under-represented population subg…
Provably Bounding Neural Network Preimages
Suhas Kotha, Christopher Brix, Zico Kolter +2
Most work on the formal verification of neural networks has focused on bounding the set of outputs that correspond to a given set of inputs (for example, bounded perturbations of a…
Interactive Concept Bottleneck Models
Kushal Chauhan, Rishabh Tiwari, Jan Freyberg +2
Concept bottleneck models (CBMs) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then predict the…
IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound
Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham +2
Recent works have tried to increase the verifiability of adversarially trained networks by running the attacks over domains larger than the original perturbations and adding variou…
(Certified!!) Adversarial Robustness for Free!
Nicholas Carlini, Florian Tramer, Krishnamurthy Dj Dvijotham +3
In this paper we show how to achieve state-of-the-art certified adversarial robustness to 2-norm bounded perturbations by relying exclusively on off-the-shelf pretrained models. To…
A Fine-Grained Analysis on Distribution Shift
Olivia Wiles, Sven Gowal, Florian Stimberg +4
Robustness to distribution shifts is critical for deploying machine learning models in the real world. Despite this necessity, there has been little work in defining the underlying…
Learning Optimal Conformal Classifiers
David Stutz, Krishnamurthy, Dvijotham +2
Modern deep learning based classifiers show very high accuracy on test data but this does not provide sufficient guarantees for safe deployment, especially in high-stake AI applica…
Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition
Alessandro De Palma, Rudy Bunel, Alban Desmaison +4
We improve the scalability of Branch and Bound (BaB) algorithms for formally proving input-output properties of neural networks. First, we propose novel bounding algorithms based o…