AI Safety

Defending LLMs against Jailbreaking Attacks via Backtranslation ACL 2024 Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normalization ICML 2024 Defense against Model Extraction Attack by Bayesian Active Watermarking ICML 2024 Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay CVPR 2024 Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models NeurIPS 2024 Detecting AI-Generated Code Assignments Using Perplexity of Large Language Models AAAI 2024 Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability IJCAI 2024 Detecting Bugs with Substantial Monetary Consequences by LLM and Rule-based Reasoning NeurIPS 2024 Detecting Mode Collapse in Language Models via Narration EACL 2024 Detection, Diagnosis, and Explanation: A Benchmark for Chinese Medical Hallucination Evaluation COLING 2024 Detector Collapse: Backdooring Object Detection to Catastrophic Overload or Blindness in the Physical World IJCAI 2024 Detoxifying Large Language Models via Knowledge Editing ACL 2024 DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models EMNLP 2024 Diffusion Models are Certifiably Robust Classifiers NeurIPS 2024 Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation ACL 2024 Direct Unlearning Optimization for Robust and Safe Text-to-Image Models NeurIPS 2024 Discovering Agents (Abstract Reprint) AAAI 2024 Disinformation Capabilities of Large Language Models ACL 2024 Distract Large Language Models for Automatic Jailbreak Attack EMNLP 2024 Diversity-Aware Annotation for Conversational AI Safety COLING 2024 D-NLP at SemEval-2024 Task 2: Evaluating Clinical Inference Capabilities of Large Language Models SemEval 2024 Do Clinicians Know How to Prompt? The Need for Automatic Prompt Optimization Help in Clinical Note Generation ACL 2024 Does Context Help Mitigate Gender Bias in Neural Machine Translation? EMNLP 2024 Does Few-Shot Learning Suffer from Backdoor Attacks? AAAI 2024 Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations? EMNLP 2024