collaborators

7 papers

cs.LG2026

Learned Compression of SAR Phase-History Data: A Rate-Honest Feasibility Study on GOTCHA

Alizishaan Khatri

On-board compression of synthetic aperture radar (SAR) phase history is bandwidth-critical, and block-adaptive quantization (BAQ) remains the operational standard. We test whether…

cs.LG2026

Same Probe, Different Numbers: Are Activation Probes Robust to Inference-Time Numerical Non-Determinism?

Alizishaan Khatri

Activation probes are increasingly used to monitor LLMs in deployment. A probe is typically trained under one inference configuration, then used under whatever batch size and numer…

cs.AI2026

Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models

Alizishaan Khatri, Chiquita Prabhu, Omkar Neogi

Autonomous systems increasingly rely on Large Language Models (LLMs) yet the safety infrastructure surrounding these models introduces latency and compute overhead. This limits uti…

cs.CR2026

Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations

Alizishaan Khatri

LLM-based code generation is now embedded in mission-critical pipelines, but defenses against vulnerable output remain post-hoc -- static analyzers, fine-tuned classifiers, or an L…

cs.LG2026

Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families

Alizishaan Khatri, Dun Li Chan

Khatri et al. (2026) [DOI: 10.1109/DSN-W70714.2026.00027] show that lightweight MLP probes on final-layer activations of a single 8B model (LLaMA-3.1-8B) detect harmful prompts at…

cs.CV2026

Latent Space Probing for Adult Content Detection in Video Generative Models

Alizishaan Khatri, Chiquita Prabhu

The rapid proliferation of AI-powered video generation systems has introduced significant challenges in content moderation, particularly with respect to adult and sexually explicit…

cs.LG2026

Preventing overfitting in deep learning using differential privacy

Alizishaan Anwar Hussein Khatri

The use of Deep Neural Network based systems in the real world is growing. They have achieved state-of-the-art performance on many image, speech and text datasets. They have been s…