← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Indecision Modeling AAAI 2021
Agent Incentives: A Causal Perspective AAAI 2021
Achieving Proportionality up to the Maximin Item with Indivisible Goods AAAI 2021
Fair and Truthful Mechanisms for Dichotomous Valuations AAAI 2021
Unifying Principles and Metrics for Safe and Assistive AI AAAI 2021
Tightening Robustness Verification of Convolutional Neural Networks with Fine-Grained Linear Approximation AAAI 2021
Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption AAAI 2021
Poisoning Knowledge Graph Embeddings via Relation Inference Patterns ACL 2021
Certified Robustness to Programmable Transformations in LSTMs EMNLP 2021
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks EMNLP 2021
Pairing Weak with Strong: Twin Models for Defending Against Adversarial Attack on Speaker Verification INTERSPEECH 2021
CARTL: Cooperative Adversarially-Robust Transfer Learning ICML 2021
Adversarial Examples in Physical World IJCAI 2021
Recent Advances in Adversarial Training for Adversarial Robustness IJCAI 2021
Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning EMNLP 2021
Multi-granularity Textual Adversarial Attack with Behavior Cloning EMNLP 2021
Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences EMNLP 2021
Improved, Deterministic Smoothing for L_1 Certified Robustness ICML 2021
Provably Efficient Actor-Critic for Risk-Sensitive and Robust Adversarial RL: A Linear-Quadratic Case AISTATS 2021
A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger’s Adversarial Attacks IJCNLP 2021
Safe Reinforcement Learning via Statistical Model Predictive Shielding RSS 2021
Recovering AES Keys with a Deep Cold Boot Attack ICML 2021
Limitations of Post-Hoc Feature Alignment for Robustness CVPR 2021
PointGuard: Provably Robust 3D Point Cloud Classification CVPR 2021
Common Sense Bias in Semantic Role Labeling EMNLP 2021