← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Defending LLMs against Jailbreaking Attacks via Backtranslation ACL 2024
Chain-of-Verification Reduces Hallucination in Large Language Models ACL 2024
Red Teaming Visual Language Models ACL 2024
TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models ACL 2024
Pseudo-Private Data Guided Model Inversion Attacks NIPS 2024
CROWD: Certified Robustness via Weight Distribution for Smoothed Classifiers against Backdoor Attack EMNLP 2024
BAN: Detecting Backdoors Activated by Adversarial Neuron Noise NIPS 2024
Provable Editing of Deep Neural Networks using Parametric Linear Relaxation NIPS 2024
Supporting Upper Elementary Students in Learning AI Concepts with Story-Driven Game-Based Learning AAAI 2024
Occlusion Sensitivity Analysis With Augmentation Subspace Perturbation in Deep Feature Space WACV 2024
Hard-Label Based Small Query Black-Box Adversarial Attack WACV 2024
Dynamic Adversarial Attacks on Autonomous Driving Systems RSS 2024
Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences NIPS 2024
Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness NIPS 2024
RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes RSS 2024
Fooling Polarization-Based Vision using Locally Controllable Polarizing Projection CVPR 2024
MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models CVPR 2024
Scanning Trojaned Models Using Out-of-Distribution Samples NIPS 2024
Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay CVPR 2024
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning CVPR 2024
1-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness CVPR 2024
Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models CVPR 2024
VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models CVPR 2024
MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model CVPR 2024
BrainWash: A Poisoning Attack to Forget in Continual Learning CVPR 2024