Alizishaan Khatri

发表论文 6 篇 · 总被引 1 次 · h-index 1

代表论文

• Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families (2026 · 被引 1)
• Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models (2026 · 2026 56th Annual IEEE International Conference on Dependable Systems and Networks Workshops (DSN-W) · 被引 1)
• What's New in TensorFlow 2.0 (2019 · 被引 1)
• Preventing overfitting in deep learning using differential privacy (2026 · arXiv.org)
• Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations (2026)
• Latent Space Probing for Adult Content Detection in Video Generative Models (2026 · 2026 56th Annual IEEE International Conference on Dependable Systems and Networks Workshops (DSN-W))