Author

Kalyan Nakka

Observed name: Nakka, Kalyan

Institution: Texas A&M University

Observed institution: Texas A&M University

ORCID: 0000-0002-3916-0939

Observed ORCID: 0000-0002-3916-0939

OpenAlex ID: A5098970411

A Machine Learning-Based Framework for Assessing Cryptographic Indistinguishability of Lightweight Block Ciphers

2025 · Jimmy Dani, Kalyan Nakka, et al. · Conference on Privacy, Security and Trust · 4

BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage

2026 · Kalyan Nakka, Nitesh Saxena · Findings of the Association for Computational Linguistics: EACL · 1

BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage

2026 · Association for Computational Linguistics 2026, Nakka, Kalyan, et al. · Underline Science Inc.

MIND-Crypt: A Machine Learning Framework for Assessing the Indistinguishability of Lightweight Block Ciphers Across Multiple Modes of Operation

2026 · Jimmy Dani, Kalyan Nakka, et al. · Cryptography

LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-induced Risks and Vulnerabilities

2025 · Nakka, Kalyan, Dani, Jimmy, et al. · arXiv (Cornell University)

LiteLMGuard: Seamless and Lightweight On-Device Guardrails for Small Language Models against Quantization Vulnerabilities

2025 · Kalyan Nakka, Jimmy Dani, et al. · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL)

Is On-Device AI Broken and Exploitable? Assessing the Trust and Ethics in Small Language Models

2024 · Nakka, Kalyan, Dani, Jimmy, et al. · arXiv (Cornell University)

Works count: 7

Citation count: 5

H-index: 1

I10-index: