AI Safety

Privacy Attacks in Decentralized Learning ICML 2024 Privacy-Preserving Instructions for Aligning Large Language Models ICML 2024 Private Truly-Everlasting Robust-Prediction ICML 2024 ProgressGym: Alignment with a Millennium of Moral Progress NeurIPS 2024 Progressive Poisoned Data Isolation for Training-Time Backdoor Defense AAAI 2024 ProMark: Proactive Diffusion Watermarking for Causal Attribution CVPR 2024 Prompt Leakage effect and mitigation strategies for multi-turn LLM Applications EMNLP 2024 Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models ICLR 2024 Proportional Representation in Metric Spaces and Low-Distortion Committee Selection AAAI 2024 Protecting Your LLMs with Information Bottleneck NeurIPS 2024 Provable Editing of Deep Neural Networks using Parametric Linear Relaxation NeurIPS 2024 Provably Safe Neural Network Controllers via Differential Dynamic Logic NeurIPS 2024 PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails ACL 2024 Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning EMNLP 2024 Pseudo-Private Data Guided Model Inversion Attacks NeurIPS 2024 PsyGUARD: An Automated System for Suicide Detection and Risk Assessment in Psychological Counseling EMNLP 2024 PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety ACL 2024 PURE: Aligning LLM via Pluggable Query Reformulation for Enhanced Helpfulness EMNLP 2024 Pure-Past Action Masking AAAI 2024 Query-Based Adversarial Prompt Generation NeurIPS 2024 Raccoon: Prompt Extraction Benchmark of LLM-Integrated Applications ACL 2024 RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes RSS 2024 RAFT: Realistic Attacks to Fool Text Detectors EMNLP 2024 RAG-HAT: A Hallucination-Aware Tuning Pipeline for LLM in Retrieval-Augmented Generation EMNLP 2024 RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors ACL 2024