Gagandeep Singh

Proc. ACM Program. Lang., 2024

IterGen: Iterative Structured LLM Generation.

[BibT_eX]

[DOI]

CoRR, 2024

Optimal Reward Labeling: Bridging Offline Preference and Reward-Based Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2024

Quantitative Certification of Bias in Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Cross-Input Certified Training for Universal Perturbations.

[BibT_eX]

[DOI]

Changming Xu

CoRR, 2024

Syndicate: Synergistic Synthesis of Ranking Function and Invariants for Termination Analysis.

[BibT_eX]

[DOI]

CoRR, 2024

ConstraintFlow: A DSL for Specification and Verification of Neural Network Analyses.

[BibT_eX]

[DOI]

CoRR, 2024

Improving LLM Code Generation with Grammar Augmentation.

[BibT_eX]

[DOI]

CoRR, 2024

QuaCer-C: Quantitative Certification of Knowledge Comprehension in LLMs.

[BibT_eX]

[DOI]

Isha Chaudhary

Vedaant V. Jain

CoRR, 2024

Reward Poisoning Attack Against Offline Reinforcement Learning.

[BibT_eX]

[DOI]

Rohan Gumaste

CoRR, 2024

Efficient Two-Phase Offline Deep Reinforcement Learning from Preference Feedback.

[BibT_eX]

[DOI]

CoRR, 2024

COMET: Neural Cost Model Explanation Framework.

[BibT_eX]

[DOI]

Proceedings of the Seventh Annual Conference on Machine Learning and Systems, 2024

Robust Universal Adversarial Perturbations.

[BibT_eX]

[DOI]

Changming Xu

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Relational DNN Verification With Cross Executional Bound Refinement.

[BibT_eX]

[DOI]

Debangshu Banerjee

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Bypassing the Safety Training of Open-Source LLMs with Priming Attacks.

[BibT_eX]

[DOI]

Proceedings of the Second Tiny Papers Track at ICLR 2024, 2024

Incremental Randomized Smoothing Certification.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Is Watermarking LLM-Generated Code Robust?

[BibT_eX]

[DOI]

Proceedings of the Second Tiny Papers Track at ICLR 2024, 2024

Exploiting Time Channel Vulnerability of Learned Bloom Filters.

[BibT_eX]

[DOI]

Harman Singh Farwah

Cheng Tan

Proceedings of the Second Tiny Papers Track at ICLR 2024, 2024

Interpreting Robustness Proofs of Deep Neural Networks.

[BibT_eX]

[DOI]

Debangshu Banerjee

Avaljot Singh

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Synthesizing Precise Static Analyzers for Automatic Differentiation.

[BibT_eX]

[DOI]

Proc. ACM Program. Lang., October, 2023

Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning.

[BibT_eX]

[DOI]

Qi Zeng

Trans. Mach. Learn. Res., 2023

Incremental Verification of Neural Networks.

[BibT_eX]

[DOI]

Proc. ACM Program. Lang., 2023

Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2023

CoMEt: x86 Cost Model Explanation Framework.

[BibT_eX]

[DOI]

CoRR, 2023

Building Trust and Safety in Artificial Intelligence with Abstract Interpretation.

[BibT_eX]

[DOI]

Proceedings of the Static Analysis - 30th International Symposium, 2023

Exploring Practical Vulnerabilities of Machine Learning-based Wireless Systems.

[BibT_eX]

[DOI]

Proceedings of the 20th USENIX Symposium on Networked Systems Design and Implementation, 2023

Provable Defense Against Geometric Transformations.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Artifact for Paper Scalable Verification of GNN-Based Job Schedulers.

[BibT_eX]

[DOI]

Dataset, September, 2022

Scalable verification of GNN-based job schedulers.

[BibT_eX]

[DOI]

Proc. ACM Program. Lang., 2022

Proof transfer for fast certification of multiple approximate neural networks.

[BibT_eX]

[DOI]

Shubham Ugare

Sasa Misailovic

Proc. ACM Program. Lang., 2022

PRIMA: general and precise neural network certification via scalable convex hull approximations.

[BibT_eX]

[DOI]

Proc. ACM Program. Lang., 2022

A general construction for abstract interpretation of higher-order automatic differentiation.

[BibT_eX]

[DOI]

Proc. ACM Program. Lang., 2022

A dual number abstraction for static analysis of Clarke Jacobians.

[BibT_eX]

[DOI]

Proc. ACM Program. Lang., 2022

Training Certifiably Robust Neural Networks Against Semantic Perturbations.

[BibT_eX]

[DOI]

CoRR, 2022

Provably Robust Adversarial Examples.

[BibT_eX]

[DOI]

Dimitar Iliev Dimitrov

Timon Gehr

Proceedings of the Tenth International Conference on Learning Representations, 2022

Shared Certificates for Neural Network Verification.

[BibT_eX]

[DOI]

Proceedings of the Computer Aided Verification - 34th International Conference, 2022

2021

Precise Multi-Neuron Abstractions for Neural Network Certification.

[BibT_eX]

[DOI]

CoRR, 2021

FIRE: enabling reciprocity for FDD MIMO systems.

[BibT_eX]

[DOI]

Proceedings of the ACM MobiCom '21: The 27th Annual International Conference on Mobile Computing and Networking, 2021

Scaling Polyhedral Neural Network Verification on GPUs.

[BibT_eX]

[DOI]

Proceedings of the Fourth Conference on Machine Learning and Systems, 2021

Robustness Certification for Point Cloud Models.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Scalable Polyhedral Verification of Recurrent Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Computer Aided Verification - 33rd International Conference, 2021

2020

Scalable Automated Reasoning for Programs and Deep Learning.

[BibT_eX]

[DOI]

PhD thesis, 2020

Scalable Inference of Symbolic Adversarial Examples.

[BibT_eX]

[DOI]

CoRR, 2020

Neural Network Robustness Verification on GPUs.

[BibT_eX]

[DOI]

CoRR, 2020

Fast and Effective Robustness Certification for Recurrent Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2020

Learning fast and precise numerical analysis.

[BibT_eX]

[DOI]

Proceedings of the 41st ACM SIGPLAN International Conference on Programming Language Design and Implementation, 2020

Adversarial Attacks on Probabilistic Autoregressive Forecasting Models.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

2019

An abstract domain for certifying neural networks.

[BibT_eX]

[DOI]

Proc. ACM Program. Lang., 2019

A Provable Defense for Deep Residual Networks.

[BibT_eX]

[DOI]

Matthew Mirman

CoRR, 2019

Beyond the Single Neuron Convex Barrier for Neural Network Certification.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Certifying Geometric Robustness of Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Boosting Robustness Certification of Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 7th International Conference on Learning Representations, 2019

2018

A practical construction for decomposing numerical abstract domains.

[BibT_eX]

[DOI]

Proc. ACM Program. Lang., 2018

Fast and Effective Robustness Certification.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Fast Numerical Program Analysis with Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Computer Aided Verification - 30th International Conference, 2018

2017

Fast polyhedra abstract domain.

[BibT_eX]

[DOI]

Proceedings of the 44th ACM SIGPLAN Symposium on Principles of Programming Languages, 2017

2015

Making numerical program analysis fast.

[BibT_eX]

[DOI]