AI Safety

On Trustworthy, Explainable, and Verifiable High-Level Autonomy via Hierarchical Planning AAAI 2026 Open-Domain Safety Policy Construction EACL 2026 Optimisation Problems in Constrained Machine Learning AAAI 2026 PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing EACL 2026 Persistent Backdoor Attacks Under Continual Fine-Tuning of LLMs AAAI 2026 Persistent Instability in LLM’s Personality Measurements: Effects of Scale, Reasoning, and Conversation History AAAI 2026 Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions EACL 2026 Perturb Your Data: Paraphrase-Guided Training Data Watermarking AAAI 2026 Phantom Menace: Exploring and Enhancing the Robustness of VLA Models Against Physical Sensor Attacks AAAI 2026 pH-Strips for Selective Forgetting: A Blunt but Fast Diagnostic Baseline for Machine Unlearning CVPR 2026 PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems AAAI 2026 Poisoned Distillation: Injecting Backdoors into Distilled Datasets Without Raw Data Access AAAI 2026 Poisoning with a Pill: Circumventing Detection in Federated Learning AAAI 2026 Policy Compliance of User Requests in Natural Language for AI Systems ACL 2026 Position: Biomedical NLP Demands Specialization, Not Generalization EACL 2026 Practising responsibility: Ethics in NLP as a hands-on course EACL 2026 Preference Optimization via Contrastive Divergence: Your Policy Is Secretly an NLL Estimator AAAI 2026 Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models CVPR 2026 Principles2Plan: LLM-Guided System for Operationalising Ethical Principles into Plans AAAI 2026 PrivSV: Differentially Private Steering Vector for Large Language Models AAAI 2026 Proactive Constrained Policy Optimization with Preemptive Penalty AAAI 2026 Probabilistic Safety Verification of Neural Policies via Predicate Abstraction AAAI 2026 Probabilistic Verification of Neural Networks via Efficient Probabilistic Hull Generation UAI 2026 Probing Semantic Insensitivity for Inference-Time Backdoor Defense in Multimodal Large Language Model AAAI 2026 Process Evaluation for Agentic Systems EACL 2026