Robustness

DDSF: Robust Few-Shot Learning via Disentangled Subspaces with Determinantal Point Process CVPR 2026 Defenses Against Prompt Attacks Learn Surface Heuristics ACL 2026 PAR: Training-Free Positional Perturbation and Attention Recycling for Faithful OCR ACL 2026 Provable Guarantees For Robust Feature Selection in Sparse Linear Models in High-Dimensions UAI 2026 Reward Sharpness-Aware Fine-Tuning for Diffusion Models CVPR 2026 Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation AISTATS 2025 Active Fourier Auditor for Estimating Distributional Properties of ML Models AAAI 2025 Adversarial-Inspired Backdoor Defense via Bridging Backdoor and Adversarial Attacks AAAI 2025 A Layer Selection Approach to Test Time Adaptation AAAI 2025 ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving ACL 2025 Bias Beware: The Impact of Cognitive Biases on LLM-Driven Product Recommendations EMNLP 2025 Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models ACL 2025 COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems Against Semantic Attacks AAAI 2025 Common Sense Bias Modeling for Classification Tasks AAAI 2025 Conflicting Needles in a Haystack: How LLMs behave when faced with contradictory information EMNLP 2025 CP$^2$: Leveraging Geometry for Conformal Prediction via Canonicalization UAI 2025 Defense Against Model Stealing Based on Account-Aware Distribution Discrepancy AAAI 2025 Designing Ambiguity Sets for Distributionally Robust Optimization Using Structural Causal Optimal Transport AAAI 2025 Distributional Adversarial Loss AISTATS 2025 Distributionally and Adversarially Robust Logistic Regression via Intersecting Wasserstein Balls UAI 2025 Does Training on Synthetic Data Make Models Less Robust? NAACL 2025 Doppelgangers and Adversarial Vulnerability CVPR 2025 Enhancing Adversarial Transferability with Adversarial Weight Tuning AAAI 2025 Enhancing Chinese Offensive Language Detection with Homophonic Perturbation EMNLP 2025 Evading Toxicity Detection with ASCII-art: A Benchmark of Spatial Attacks on Moderation Systems ACL 2025