Prateek Mittal

AcoustoReinforce: Multi-Particle Acoustophoretic Path Planning with Deep Reinforcement Learning AAAI 2026 Adapting to Evolving Adversaries with Regularized Continual Robust Training ICML 2025 Capturing the Temporal Dependence of Training Data Influence ICLR 2025 Data Shapley in One Training Run ICLR 2025 Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy ICLR 2025 On Evaluating the Durability of Safeguards for Open-Weight LLMs ICLR 2025 PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches CVPR 2025 Privacy Auditing of Large Language Models ICLR 2025 Safety Alignment Should be Made More Than Just a Few Tokens Deep ICLR 2025 SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal ICLR 2025 A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization ICML 2024 Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications ICML 2024 BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection ICLR 2024 BrainLM: A foundation model for brain activity recordings ICLR 2024 Efficient Data Shapley for Weighted Nearest Neighbor Algorithms AISTATS 2024 Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! ICLR 2024 GREATS: Online Selection of High-Quality Data for LLM Training in Every Iteration NeurIPS 2024 Privacy-Preserving In-Context Learning for Large Language Models ICLR 2024 Teach LLMs to Phish: Stealing Private Information from Language Models ICLR 2024 Visual Adversarial Examples Jailbreak Aligned Large Language Models AAAI 2024 A Privacy-Friendly Approach to Data Valuation NeurIPS 2023 A Randomized Approach to Tight Privacy Accounting NeurIPS 2023 Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker NeurIPS 2023 Differentially Private Image Classification by Learning Priors from Random Processes NeurIPS 2023 Effectively Using Public Data in Privacy Preserving Machine Learning ICML 2023 MultiRobustBench: Benchmarking Robustness Against Multiple Attacks ICML 2023 Revisiting the Assumption of Latent Separability for Backdoor Defenses ICLR 2023 Uncovering Adversarial Risks of Test-Time Adaptation ICML 2023 Formulating Robustness Against Unforeseen Attacks NeurIPS 2022 Neurotoxin: Durable Backdoors in Federated Learning ICML 2022 Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning NeurIPS 2022 Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness? ICLR 2022 SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification AISTATS 2022 Understanding Robust Learning through the Lens of Representation Similarities NeurIPS 2022 Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries ICML 2021 SSD: A Unified Framework for Self-Supervised Outlier Detection ICLR 2021 HYDRA: Pruning Adversarially Robust Neural Networks NeurIPS 2020 Analyzing Federated Learning through an Adversarial Lens ICML 2019 Lower Bounds on Adversarial Robustness from Optimal Transport NeurIPS 2019 PAC-learning in the presence of adversaries NeurIPS 2018