Get started
Author

Alizishaan Khatri

Observed name: Khatri, Alizishaan
ORCID: 0000-0001-5531-3635
Observed ORCID: 0000-0001-5531-3635
OpenAlex ID: A5039279679
Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models
2026 · Alizishaan Khatri, Chiquita Prabhu, et al. · International Conference on Dependable Systems and Networks workshops · 3
PDF
Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families
2026 · Alizishaan Khatri, Dun Li Chan · SSRN Electronic Journal · 2
Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations
2026 · Khatri, Alizishaan · arXiv (Cornell University) · 1
PDF
Safety Beyond the Interface: Detecting Harm via Latent LLM States
2026 · Alizishaan Khatri, Chiquita Prabhu, et al. · SSRN Electronic Journal · 1
Same Probe, Different Numbers: Are Activation Probes Robust to Inference-Time Numerical Non-Determinism?
2026 · Khatri, Alizishaan · arXiv (Cornell University)
PDF
Learned Compression of SAR Phase-History Data: A Rate-Honest Feasibility Study on GOTCHA
2026 · Khatri, Alizishaan · arXiv (Cornell University)
PDF
Latent Space Probing for Adult Content Detection in Video Generative Models
2026 · Alizishaan Khatri, Chiquita Prabhu · International Conference on Dependable Systems and Networks workshops
PDF
Safety Beyond the Interface: Detecting Harm via Latent LLM States
2026 · Khatri, Alizishaan, Prabhu, Chiquita, et al. · Zenodo (CERN European Organization for Nuclear Research)
Safety Beyond the Interface: Detecting Harm via Latent LLM States
2026 · Alizishaan Khatri, Prabhu, Chiquita, et al.
Latent Space Probing for Adult Content Detection in Video Generative Models
2026 · Alizishaan Khatri, Prabhu, Chiquita
What's New in TensorFlow 2.0
2019 · Ajay Kumar Baranwal, Alizishaan Khatri, et al.
Works count: 11
Citation count: 7
H-index: 2
I10-index:
Year
Topic
Type