AI Safety

Backdoor Contrastive Learning via Bi-level Trigger Optimization ICLR 2024 Backdoor Defense via Test-Time Detecting and Repairing CVPR 2024 Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection NAACL 2024 Backdoor NLP Models via AI-Generated Text COLING 2024 Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency ICLR 2024 Backward Responsibility in Transition Systems Using General Power Indices AAAI 2024 BadActs: A Universal Backdoor Defense in the Activation Space ACL 2024 BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents ACL 2024 BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models ICLR 2024 BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning CVPR 2024 BadEdit: Backdooring Large Language Models by Model Editing ICLR 2024 BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection ICLR 2024 BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers EMNLP 2024 BADFSS: Backdoor Attacks on Federated Self-Supervised Learning IJCAI 2024 BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks (Student Abstract) AAAI 2024 Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs NeurIPS 2024 BaitAttack: Alleviating Intention Shift in Jailbreak Attacks via Adaptive Bait Crafting EMNLP 2024 BAIT: Benchmarking (Embedding) Architectures for Interactive Theorem-Proving AAAI 2024 Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation AAAI 2024 BAN: Detecting Backdoors Activated by Adversarial Neuron Noise NeurIPS 2024 Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming EMNLP 2024 BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models EMNLP 2024 Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks ICML 2024 Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment ICLR 2024 Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints ICLR 2024