Tag: adversarial robustness
Browse our exclusive articles!
Latent Personality Alignment: Boost AI Harmlessness Efficiently
Discover Latent Personality Alignment, a novel method enhancing AI harmlessness with fewer data and superior robustness against harmful prompts.
Testing Adversarial Robustness of RL-Trained Empathetic Agents
Explore how RL-trained empathetic agents withstand adversarial emotional scenarios using the Adversarial Empathy Benchmark and Emotional Consistency Score.
ArmSSL: Robust Black-Box Watermarking for SSL Encoders
ArmSSL offers adversarially robust black-box watermarking to secure self-supervised learning encoders with reliable ownership verification.
Hierarchically Robust Zero-Shot Vision-Language Models
Discover how hierarchical embeddings improve adversarial robustness in zero-shot vision-language models for enhanced performance and security.
Multi-Objective LLM Unlearning with Unified Data & Distillation
Discover a novel LLM unlearning framework that balances efficacy, utility, and robustness using unified domain representation and bidirectional logit disti...