Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Defeasible Normative Reasoning: A Proof-Theoretic Integration of Logical Argumentation AAAI 2024

BAIT: Benchmarking (Embedding) Architectures for Interactive Theorem-Proving AAAI 2024

Consistency-Guided Temperature Scaling Using Style and Content Information for Out-of-Domain Calibration AAAI 2024

Lyapunov-Stable Deep Equilibrium Models AAAI 2024

REGLO: Provable Neural Network Repair for Global Robustness Properties AAAI 2024

DeepSaDe: Learning Neural Networks That Guarantee Domain Constraint Satisfaction AAAI 2024

Exploring Channel-Aware Typical Features for Out-of-Distribution Detection AAAI 2024

Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning AAAI 2024

Meta-Learning-Based Adaptive Stability Certificates for Dynamical Systems AAAI 2024

Adaptive Shortcut Debiasing for Online Continual Learning AAAI 2024

Twice Class Bias Correction for Imbalanced Semi-supervised Learning AAAI 2024

On the Convergence of an Adaptive Momentum Method for Adversarial Attacks AAAI 2024

Federated Learning with Extremely Noisy Clients via Negative Distillation AAAI 2024

SafeAR: Safe Algorithmic Recourse by Risk-Aware Policies AAAI 2024

Chronic Poisoning: Backdoor Attack against Split Learning AAAI 2024

What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection AAAI 2024

Conditional Backdoor Attack via JPEG Compression AAAI 2024

Does Few-Shot Learning Suffer from Backdoor Attacks? AAAI 2024

Find the Lady: Permutation and Re-synchronization of Deep Neural Networks AAAI 2024

Stability Analysis of Switched Linear Systems with Neural Lyapunov Functions AAAI 2024

Robustness Verification of Multi-Class Tree Ensembles AAAI 2024

A Simple and Yet Fairly Effective Defense for Graph Neural Networks AAAI 2024

Stronger and Transferable Node Injection Attacks AAAI 2024

NeRFail: Neural Radiance Fields-Based Multiview Adversarial Attack AAAI 2024

Raccoon: Prompt Extraction Benchmark of LLM-Integrated Applications ACL 2024