Gagandeep Singh

108 papers A* 21B 3Misc 1Journal 71Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Efficient Ranking Function-Based Termination Analysis via Bidirectional Decompositional Search. ESOP (2) Yasmin Sarita, Avaljot Singh, Shaurya Gomber, Gagandeep Singh, Mahesh Vishwanathan
2026	J	`jnl`	Formal Synthesis of Certifiably Robust Neural Lyapunov-Barrier Certificates. CoRR Chengxiao Wang, Haoze Wu, Gagandeep Singh
2026	J	`jnl`	SEVerA: Verified Synthesis of Self-Evolving Agents. CoRR Debangshu Banerjee, Changming Xu, Gagandeep Singh
2025	J	`jnl`	A Tensor-Based Compiler and a Runtime for Neuron-Level DNN Certifier Specifications. CoRR Avaljot Singh, Yamin Chandini Sarita, Aditya Mishra, Ishaan Goyal, Gagandeep Singh, Charith Mendis
2025	J	`jnl`	Automated Verification of Soundness of DNN Certifiers. CoRR Avaljot Singh, Yasmin Sarita, Charith Mendis, Gagandeep Singh
2025	J	`jnl`	Automated Verification of Soundness of DNN Certifiers. Proc. ACM Program. Lang. Avaljot Singh, Yasmin Sarita, Charith Mendis, Gagandeep Singh
2025	J	`jnl`	BEAVER: An Efficient Deterministic LLM Verifier. CoRR Tarun Suresh, Nalin Wadhwa, Debangshu Banerjee, Gagandeep Singh
2025	A*	`conf`	CRANE: Reasoning with constrained LLM generation. ICML Debangshu Banerjee, Tarun Suresh, Shubham Ugare, Sasa Misailovic, Gagandeep Singh
2025	J	`jnl`	CRANE: Reasoning with constrained LLM generation. CoRR Debangshu Banerjee, Tarun Suresh, Shubham Ugare, Sasa Misailovic, Gagandeep Singh
2025	A*	`conf`	Certifying Counterfactual Bias in LLMs. ICLR Isha Chaudhary, Qian Hu, Manoj Kumar, Morteza Ziyadi, Rahul Gupta, Gagandeep Singh
2025	J	`jnl`	Cost-Driven Synthesis of Sound Abstract Interpreters. CoRR Qiuhan Gu, Avaljot Singh, Gagandeep Singh
2025	J	`jnl`	DINGO: Constrained Inference for Diffusion LLMs. CoRR Tarun Suresh, Debangshu Banerjee, Shubham Ugare, Sasa Misailovic, Gagandeep Singh
2025	J	`jnl`	Data Shifts Hurt CoT: A Theoretical Study. CoRR Lang Yin, Debangshu Banerjee, Gagandeep Singh
2025	J	`jnl`	Enforcing Temporal Constraints for LLM Agents. CoRR Adharsh Kamath, Sishen Zhang, Calvin Xu, Shubham Ugare, Gagandeep Singh, Sasa Misailovic
2025	J	`jnl`	Improving Assembly Code Performance with Large Language Models via Reinforcement Learning. CoRR Anjiang Wei, Tarun Suresh, Huanmi Tan, Yinglun Xu, Gagandeep Singh, Ke Wang, Alex Aiken
2025	A*	`conf`	IterGen: Iterative Semantic-aware Structured LLM Generation with Backtracking. ICLR Shubham Ugare, Rohan Gumaste, Tarun Suresh, Gagandeep Singh, Sasa Misailovic
2025	J	`jnl`	Learning a Pessimistic Reward Model in RLHF. CoRR Yinglun Xu, Hangoo Kang, Tarun Suresh, Yuxuan Wan, Gagandeep Singh
2025	J	`jnl`	Lumos: Let there be Language Model System Certification. CoRR Isha Chaudhary, Vedaant V. Jain, Avaljot Singh, Kavya Sachdeva, Sayan Ranu, Gagandeep Singh
2025	J	`jnl`	Matching Ranks Over Probability Yields Truly Deep Safety Alignment. CoRR Jason Vega, Gagandeep Singh
2025	J	`jnl`	Preface of the special issue on the static analysis symposium 2020 and 2022. Formal Methods Syst. Des. David Pichardie, Mihaela Sighireanu, Gagandeep Singh, Caterina Urban
2025	J	`jnl`	Quantifying Distributional Robustness of Agentic Tool-Selection. CoRR Jehyeok Yeon, Isha Chaudhary, Gagandeep Singh
2025	J	`jnl`	Quantifying Risks in Multi-turn Conversation with Large Language Models. CoRR Chengxiao Wang, Isha Chaudhary, Qian Hu, Weitong Ruan, Rahul Gupta, Gagandeep Singh
2025	J	`jnl`	Safety and Trust in Artificial Intelligence with Abstract Interpretation. Found. Trends Program. Lang. Gagandeep Singh, Jacob Laurel, Sasa Misailovic, Debangshu Banerjee, Avaljot Singh, Changming Xu, Shubham Ugare, Huan Zhang
2025	A*	`conf`	Support is All You Need for Certified VAE Training. ICLR Changming Xu, Debangshu Banerjee, Deepak Vasisht, Gagandeep Singh
2025	J	`jnl`	Support is All You Need for Certified VAE Training. CoRR Changming Xu, Debangshu Banerjee, Deepak Vasisht, Gagandeep Singh
2025	J	`jnl`	SynCode: LLM Generation with Grammar Augmentation. Trans. Mach. Learn. Res. Shubham Ugare, Tarun Suresh, Hangoo Kang, Sasa Misailovic, Gagandeep Singh
2025	J	`jnl`	TRAP: Targeted Redirecting of Agentic Preferences. CoRR Hangoo Kang, Jehyeok Yeon, Gagandeep Singh
2025	J	`jnl`	Two-Step Offline Preference-Based Reinforcement Learning on Explicitly Constrained Policies. Trans. Mach. Learn. Res. Yinglun Xu, Tarun Suresh, Rohan Gumaste, David Zhu, Ruirui Li, Zhengyang Wang, Haoming Jiang, Xianfeng Tang, Qingyu Yin, Monica Xiao Cheng, Qi Zeng, Chao Zhang, Gagandeep Singh
2025	J	`jnl`	UTF-8 Plumbing: Byte-level Tokenizers Unavoidably Enable LLMs to Generate Ill-formed UTF-8. CoRR Preston Firestone, Shubham Ugare, Gagandeep Singh, Sasa Misailovic
2025	J	`jnl`	Universal Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning. Trans. Mach. Learn. Res. Yinglun Xu, Gagandeep Singh
2025	J	`jnl`	Universal Synthesis of Differentiably Tunable Numerical Abstract Transformers. CoRR Shaurya Gomber, Debangshu Banerjee, Gagandeep Singh
2024	J	`jnl`	ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs. CoRR Yuchen Yang, Shubham Ugare, Yifan Zhao, Gagandeep Singh, Sasa Misailovic
2024	—	`conf`	Bypassing the Safety Training of Open-Source LLMs with Priming Attacks. Tiny Papers @ ICLR Jason Vega, Isha Chaudhary, Changming Xu, Gagandeep Singh
2024	—	`conf`	COMET: Neural Cost Model Explanation Framework. MLSys Isha Chaudhary, Alex Renda, Charith Mendis, Gagandeep Singh
2024	J	`jnl`	ConstraintFlow: A DSL for Specification and Verification of Neural Network Analyses. CoRR Avaljot Singh, Yasmin Sarita, Charith Mendis, Gagandeep Singh
2024	B	`conf`	ConstraintFlow: A Declarative DSL for Easy Development of DNN Certifiers. SAS Avaljot Singh, Yasmin Sarita, Charith Mendis, Gagandeep Singh
2024	—	`conf`	Cross-Input Certified Training for Universal Perturbations. ECCV (65) Changming Xu, Gagandeep Singh
2024	J	`jnl`	Cross-Input Certified Training for Universal Perturbations. CoRR Changming Xu, Gagandeep Singh
2024	J	`jnl`	Efficient Two-Phase Offline Deep Reinforcement Learning from Preference Feedback. CoRR Yinglun Xu, Gagandeep Singh
2024	—	`conf`	Exploiting Time Channel Vulnerability of Learned Bloom Filters. Tiny Papers @ ICLR Harman Singh Farwah, Gagandeep Singh, Cheng Tan
2024	J	`jnl`	Improving LLM Code Generation with Grammar Augmentation. CoRR Shubham Ugare, Tarun Suresh, Hangoo Kang, Sasa Misailovic, Gagandeep Singh
2024	A*	`conf`	Incremental Randomized Smoothing Certification. ICLR Shubham Ugare, Tarun Suresh, Debangshu Banerjee, Gagandeep Singh, Sasa Misailovic
2024	J	`jnl`	Input-Relational Verification of Deep Neural Networks. Proc. ACM Program. Lang. Debangshu Banerjee, Changming Xu, Gagandeep Singh
2024	A*	`conf`	Interpreting Robustness Proofs of Deep Neural Networks. ICLR Debangshu Banerjee, Avaljot Singh, Gagandeep Singh
2024	—	`conf`	Is Watermarking LLM-Generated Code Robust? Tiny Papers @ ICLR Tarun Suresh, Shubham Ugare, Gagandeep Singh, Sasa Misailovic
2024	J	`jnl`	Is Watermarking LLM-Generated Code Robust? CoRR Tarun Suresh, Shubham Ugare, Gagandeep Singh, Sasa Misailovic
2024	J	`jnl`	IterGen: Iterative Structured LLM Generation. CoRR Shubham Ugare, Rohan Gumaste, Tarun Suresh, Gagandeep Singh, Sasa Misailovic
2024	A*	`conf`	NN4SysBench: Characterizing Neural Network Verification for Computer Systems. NeurIPS Shuyi Lin, Haoyu He, Tianhao Wei, Kaidi Xu, Huan Zhang, Gagandeep Singh, Changliu Liu, Cheng Tan
2024	J	`jnl`	Optimal Reward Labeling: Bridging Offline Preference and Reward-Based Reinforcement Learning. CoRR Yinglun Xu, David Zhu, Rohan Gumaste, Gagandeep Singh
2024	J	`jnl`	QuaCer-C: Quantitative Certification of Knowledge Comprehension in LLMs. CoRR Isha Chaudhary, Vedaant V. Jain, Gagandeep Singh
2024	J	`jnl`	Quantitative Certification of Bias in Large Language Models. CoRR Isha Chaudhary, Qian Hu, Manoj Kumar, Morteza Ziyadi, Rahul Gupta, Gagandeep Singh
2024	A*	`conf`	Relational DNN Verification With Cross Executional Bound Refinement. ICML Debangshu Banerjee, Gagandeep Singh
2024	J	`jnl`	Relational DNN Verification With Cross Executional Bound Refinement. CoRR Debangshu Banerjee, Gagandeep Singh
2024	A*	`conf`	Relational Verification Leaps Forward with RABBit. NeurIPS Tarun Suresh, Debangshu Banerjee, Gagandeep Singh
2024	J	`jnl`	Reward Poisoning Attack Against Offline Reinforcement Learning. CoRR Yinglun Xu, Rohan Gumaste, Gagandeep Singh
2024	J	`jnl`	Robust Thompson Sampling Algorithms Against Reward Poisoning Attacks. CoRR Yinglun Xu, Zhiwei Wang, Gagandeep Singh
2024	A*	`conf`	Robust Universal Adversarial Perturbations. ICML Changming Xu, Gagandeep Singh
2024	J	`jnl`	Specification Generation for Neural Networks in Systems. CoRR Isha Chaudhary, Shuyi Lin, Cheng Tan, Gagandeep Singh
2024	J	`jnl`	Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment. CoRR Jason Vega, Junsheng Huang, Gaokai Zhang, Hangoo Kang, Minjia Zhang, Gagandeep Singh
2024	J	`jnl`	Syndicate: Synergistic Synthesis of Ranking Function and Invariants for Termination Analysis. CoRR Yasmin Sarita, Avaljot Singh, Shaurya Gomber, Gagandeep Singh, Mahesh Vishwanathan
2023	J	`jnl`	Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning. CoRR Yinglun Xu, Gagandeep Singh
2023	B	`conf`	Building Trust and Safety in Artificial Intelligence with Abstract Interpretation. SAS Gagandeep Singh
2023	J	`jnl`	Bypassing the Safety Training of Open-Source LLMs with Priming Attacks. CoRR Jason Vega, Isha Chaudhary, Changming Xu, Gagandeep Singh
2023	J	`jnl`	CoMEt: x86 Cost Model Explanation Framework. CoRR Isha Chaudhary, Alex Renda, Charith Mendis, Gagandeep Singh
2023	J	`jnl`	Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning. Trans. Mach. Learn. Res. Yinglun Xu, Qi Zeng, Gagandeep Singh
2023	Misc	`conf`	Exploring Practical Vulnerabilities of Machine Learning-based Wireless Systems. NSDI Zikun Liu, Changming Xu, Emerson Sie, Gagandeep Singh, Deepak Vasisht
2023	J	`jnl`	Incremental Randomized Smoothing Certification. CoRR Shubham Ugare, Tarun Suresh, Debangshu Banerjee, Gagandeep Singh, Sasa Misailovic
2023	J	`jnl`	Incremental Verification of Neural Networks. CoRR Shubham Ugare, Debangshu Banerjee, Sasa Misailovic, Gagandeep Singh
2023	J	`jnl`	Incremental Verification of Neural Networks. Proc. ACM Program. Lang. Shubham Ugare, Debangshu Banerjee, Sasa Misailovic, Gagandeep Singh
2023	J	`jnl`	Interpreting Robustness Proofs of Deep Neural Networks. CoRR Debangshu Banerjee, Avaljot Singh, Gagandeep Singh
2023	A*	`conf`	Provable Defense Against Geometric Transformations. ICLR Rem Yang, Jacob Laurel, Sasa Misailovic, Gagandeep Singh
2023	J	`jnl`	Synthesizing Precise Static Analyzers for Automatic Differentiation. Proc. ACM Program. Lang. Jacob Laurel, Siyuan Brant Qian, Gagandeep Singh, Sasa Misailovic
2022	J	`jnl`	A dual number abstraction for static analysis of Clarke Jacobians. Proc. ACM Program. Lang. Jacob Laurel, Rem Yang, Gagandeep Singh, Sasa Misailovic
2022	J	`jnl`	A general construction for abstract interpretation of higher-order automatic differentiation. Proc. ACM Program. Lang. Jacob Laurel, Rem Yang, Shubham Ugare, Robert Nagel, Gagandeep Singh, Sasa Misailovic
2022	J	`jnl`	Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning. CoRR Yinglun Xu, Qi Zeng, Gagandeep Singh
2022	J	`jnl`	PRIMA: general and precise neural network certification via scalable convex hull approximations. Proc. ACM Program. Lang. Mark Niklas Müller, Gleb Makarchuk, Gagandeep Singh, Markus Püschel, Martin T. Vechev
2022	J	`jnl`	Proof transfer for fast certification of multiple approximate neural networks. Proc. ACM Program. Lang. Shubham Ugare, Gagandeep Singh, Sasa Misailovic
2022	A*	`conf`	Provably Robust Adversarial Examples. ICLR Dimitar Iliev Dimitrov, Gagandeep Singh, Timon Gehr, Martin T. Vechev
2022	J	`jnl`	Robust Universal Adversarial Perturbations. CoRR Changming Xu, Gagandeep Singh
2022	J	`jnl`	Scalable Verification of GNN-based Job Schedulers. CoRR Haoze Wu, Clark W. Barrett, Mahmood Sharif, Nina Narodytska, Gagandeep Singh
2022	J	`jnl`	Scalable verification of GNN-based job schedulers. Proc. ACM Program. Lang. Haoze Wu, Clark W. Barrett, Mahmood Sharif, Nina Narodytska, Gagandeep Singh
2022	—	`conf`	Shared Certificates for Neural Network Verification. CAV (1) Marc Fischer, Christian Sprecher, Dimitar I. Dimitrov, Gagandeep Singh, Martin T. Vechev
2022	B	`ed.`	Static Analysis - 29th International Symposium, SAS 2022, Auckland, New Zealand, December 5-7, 2022, Proceedings SAS Gagandeep Singh, Caterina Urban
2022	J	`jnl`	Training Certifiably Robust Neural Networks Against Semantic Perturbations. CoRR Rem Yang, Jacob Laurel, Sasa Misailovic, Gagandeep Singh
2021	A*	`conf`	FIRE: enabling reciprocity for FDD MIMO systems. MobiCom Zikun Liu, Gagandeep Singh, Chenren Xu, Deepak Vasisht
2021	J	`jnl`	Precise Multi-Neuron Abstractions for Neural Network Certification. CoRR Mark Niklas Müller, Gleb Makarchuk, Gagandeep Singh, Markus Püschel, Martin T. Vechev
2021	A*	`conf`	Robustness Certification for Point Cloud Models. ICCV Tobias Lorenz, Anian Ruoss, Mislav Balunovic, Gagandeep Singh, Martin T. Vechev
2021	J	`jnl`	Robustness Certification for Point Cloud Models. CoRR Tobias Lorenz, Anian Ruoss, Mislav Balunovic, Gagandeep Singh, Martin T. Vechev
2021	—	`conf`	Scalable Polyhedral Verification of Recurrent Neural Networks. CAV (1) Wonryong Ryou, Jiayu Chen, Mislav Balunovic, Gagandeep Singh, Andrei Marian Dan, Martin T. Vechev
2021	—	`conf`	Scaling Polyhedral Neural Network Verification on GPUs. MLSys Christoph Müller, François Serre, Gagandeep Singh, Markus Püschel, Martin T. Vechev
2021	J	`jnl`	Shared Certificates for Neural Network Verification. CoRR Christian Sprecher, Marc Fischer, Dimitar I. Dimitrov, Gagandeep Singh, Martin T. Vechev
2020	A*	`conf`	Adversarial Attacks on Probabilistic Autoregressive Forecasting Models. ICML Raphaël Dang-Nhu, Gagandeep Singh, Pavol Bielik, Martin T. Vechev
2020	J	`jnl`	Adversarial Attacks on Probabilistic Autoregressive Forecasting Models. CoRR Raphaël Dang-Nhu, Gagandeep Singh, Pavol Bielik, Martin T. Vechev
2020	J	`jnl`	Fast and Effective Robustness Certification for Recurrent Neural Networks. CoRR Wonryong Ryou, Jiayu Chen, Mislav Balunovic, Gagandeep Singh, Andrei Marian Dan, Martin T. Vechev
2020	A*	`conf`	Learning fast and precise numerical analysis. PLDI Jingxuan He, Gagandeep Singh, Markus Püschel, Martin T. Vechev
2020	J	`jnl`	Neural Network Robustness Verification on GPUs. CoRR Christoph Müller, Gagandeep Singh, Markus Püschel, Martin T. Vechev
2020	—	`—`	Scalable Automated Reasoning for Programs and Deep Learning. Gagandeep Singh
2020	J	`jnl`	Scalable Inference of Symbolic Adversarial Examples. CoRR Dimitar I. Dimitrov, Gagandeep Singh, Timon Gehr, Martin T. Vechev
2019	J	`jnl`	A Provable Defense for Deep Residual Networks. CoRR Matthew Mirman, Gagandeep Singh, Martin T. Vechev
2019	J	`jnl`	An abstract domain for certifying neural networks. Proc. ACM Program. Lang. Gagandeep Singh, Timon Gehr, Markus Püschel, Martin T. Vechev
2019	A*	`conf`	Beyond the Single Neuron Convex Barrier for Neural Network Certification. NeurIPS Gagandeep Singh, Rupanshu Ganvir, Markus Püschel, Martin T. Vechev
2019	—	`conf`	Boosting Robustness Certification of Neural Networks. ICLR (Poster) Gagandeep Singh, Timon Gehr, Markus Püschel, Martin T. Vechev
2019	A*	`conf`	Certifying Geometric Robustness of Neural Networks. NeurIPS Mislav Balunovic, Maximilian Baader, Gagandeep Singh, Timon Gehr, Martin T. Vechev
2018	J	`jnl`	A practical construction for decomposing numerical abstract domains. Proc. ACM Program. Lang. Gagandeep Singh, Markus Püschel, Martin T. Vechev
2018	—	`conf`	Fast Numerical Program Analysis with Reinforcement Learning. CAV (1) Gagandeep Singh, Markus Püschel, Martin T. Vechev
2018	A*	`conf`	Fast and Effective Robustness Certification. NeurIPS Gagandeep Singh, Timon Gehr, Matthew Mirman, Markus Püschel, Martin T. Vechev
2017	A*	`conf`	Fast polyhedra abstract domain. POPL Gagandeep Singh, Markus Püschel, Martin T. Vechev
2015	A*	`conf`	Making numerical program analysis fast. PLDI Gagandeep Singh, Markus Püschel, Martin T. Vechev