← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

IDGuard: Robust General Identity-centric POI Proactive Defense Against Face Editing Abuse CVPR 2024
Gradient Alignment for Cross-Domain Face Anti-Spoofing CVPR 2024
RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback CVPR 2024
HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data CVPR 2024
MMA-Diffusion: MultiModal Attack on Diffusion Models CVPR 2024
CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion CVPR 2024
Backdoor Defense via Test-Time Detecting and Repairing CVPR 2024
A Framework for Approaching AI Education in Educator Preparation Programs AAAI 2024
AI Evaluation Authorities: A Case Study Mapping Model Audits to Persistent Standards AAAI 2024
U-trustworthy Models. Reliability, Competence, and Confidence in Decision-Making AAAI 2024
IPRemover: A Generative Model Inversion Attack against Deep Neural Network Fingerprinting and Watermarking AAAI 2024
Aligning Model Properties via Conformal Risk Control NIPS 2024
On the Scalability of Certified Adversarial Robustness with Generated Data NIPS 2024
SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions NIPS 2024
Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients NIPS 2024
SuperDeepFool: a new fast and accurate minimal adversarial attack NIPS 2024
Improved Generation of Adversarial Examples Against Safety-aligned LLMs NIPS 2024
Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies NIPS 2024
Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context NIPS 2024
Critically Assessing the State of the Art in Neural Network Verification JMLR 2024
Inspecting Prediction Confidence for Detecting Black-Box Backdoor Attacks AAAI 2024
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch EMNLP 2024
Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations EMNLP 2024
A Test Suite of Prompt Injection Attacks for LLM-based Machine Translation EMNLP 2024
Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors EMNLP 2024