input perturbation

Learning Representations from Perturbation: A Novel Matrix-View Weighting Framework for Naive Bayes UAI 2026 Maximally Robust Satisficing Bayesian Optimization UAI 2026 ORSO QGen: Odds-Ratio Steerable Optimization for Controlling Question Generation EACL 2026 PINet: Improving the Stability of Prototype Networks via Phantasia-Inspired Uncertain Representations AAAI 2026 An Automatic Method to Estimate Correctness of RAG COLING 2025 Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems EMNLP 2025 Differentially Private Range Queries with Correlated Input Perturbation AISTATS 2025 Speech Robust Bench: A Robustness Benchmark For Speech Recognition ICLR 2025 UFID: A Unified Framework for Black-box Input-level Backdoor Detection on Diffusion Models AAAI 2025 Accelerating Adversarially Robust Model Selection for Deep Neural Networks via Racing AAAI 2024 Doubly Perturbed Task Free Continual Learning AAAI 2024 Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets EMNLP 2024 Evaluating Robustness of Open Dialogue Summarization Models in the Presence of Naturally Occurring Variations ACL 2024 Investigating the Role of Instruction Variety and Task Difficulty in Robotic Manipulation Tasks EMNLP 2024 Perturb-and-Project: Differentially Private Similarities and Marginals ICML 2024 Input Perturbation Reduces Exposure Bias in Diffusion Models ICML 2023 [MASK] Insertion: a robust method for anti-adversarial attacks EACL 2023 On the Robustness of Removal-Based Feature Attributions NeurIPS 2023 Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text EMNLP 2023 An Explainable Toolbox for Evaluating Pre-trained Vision-Language Models EMNLP 2022 Being Friends Instead of Adversaries: Deep Networks Learn from Data Simplified by Other Networks AAAI 2022 Certifiably Robust Variational Autoencoders AISTATS 2022 Combating Adversaries with Anti-adversaries AAAI 2022 Fairness Reprogramming NeurIPS 2022 Prediction Difference Regularization against Perturbation for Neural Machine Translation ACL 2022