Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

The Perils of Learning From Unlabeled Data: Backdoor Attacks on Semi-supervised Learning ICCV 2023

Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence ICCV 2023

An Embarrassingly Simple Backdoor Attack on Self-supervised Learning ICCV 2023

CGBA: Curvature-aware Geometric Black-box Attack ICCV 2023

Robust Evaluation of Diffusion-Based Adversarial Purification ICCV 2023

Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples ICCV 2023

Unified Adversarial Patch for Cross-Modal Attacks in the Physical World ICCV 2023

Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting ICCV 2023

Beating Backdoor Attack at Its Own Game ICCV 2023

Structure Invariant Transformation for better Adversarial Transferability ICCV 2023

Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning ICCV 2023

CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning ICCV 2023

One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training ICCV 2023

How to Choose your Best Allies for a Transferable Attack? ICCV 2023

SSDA: Secure Source-Free Domain Adaptation ICCV 2023

Towards Building More Robust Models with Frequency Bias ICCV 2023

Unified Out-Of-Distribution Detection: A Model-Specific Perspective ICCV 2023

Activate and Reject: Towards Safe Domain Generalization under Category Shift ICCV 2023

Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection AAAI 2023

Auditing and Robustifying COVID-19 Misinformation Datasets via Anticontent Sampling AAAI 2023

Rethinking Safe Control in the Presence of Self-Seeking Humans AAAI 2023

Multispectral Invisible Coating: Laminated Visible-Thermal Physical Attack against Multispectral Object Detectors Using Transparent Low-E Films AAAI 2023

Contrastive Self-Supervised Learning Leads to Higher Adversarial Susceptibility AAAI 2023

Defending from Physically-Realizable Adversarial Attacks through Internal Over-Activation Analysis AAAI 2023

Targeted Knowledge Infusion To Make Conversational AI Explainable and Safe AAAI 2023