DK
Divyanshu Kumar
cs.AIcs.CLcs.CRcs.CYcs.HCcs.IRcs.MM
On Valency
published · living versionsW_vk6fggtt·v1 · currentpublished
JevBreak: Your Model, Their Decision
with Nitin Aravind Birur, Sahil Agarwal, Prashanth Harshangi
1 version
Preprints & journals
12 papers in the corpus · 2024–2026The Agent Incident Registry: Toward Preventing Repeated AI Agent Failures2609.11030v2 · Divyanshu Kumar, Rohith HN, Nitin Aravind Birur et al.2026 · 0 citationsarXiv
Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery2609.09647v1 · Divyanshu Kumar, Nitin Aravind Birur, Tanay Baswa et al.2026 · 0 citationsarXiv
SocioEval: A Template-Based Framework for Evaluating Socioeconomic Status Bias in Foundation Models2604.02660v1 · Divyanshu Kumar, Ishita Gupta, Nitin Aravind Birur et al.2026 · 0 citationsarXiv
Redirected, Not Removed: Task-Dependent Stereotyping Reveals the Limits of LLM Alignments2604.02669v1 · Divyanshu Kumar, Ishita Gupta, Nitin Aravind Birur et al.2026 · 0 citationsarXiv
Quantifying CBRN Risk in Frontier Models2510.21133v1 · Divyanshu Kumar, Nitin Aravind Birur, Tanay Baswa et al.2025 · 1 citationarXiv
Beyond Text: Multimodal Jailbreaking of Vision-Language and Audio Models through Perceptually Simple Transformations2510.20223v1 · Divyanshu Kumar, Shreyas Jena, Nitin Aravind Birur et al.2025 · 0 citationsarXiv
Beyond Western Politics: Cross-Cultural Benchmarks for Evaluating Partisan Associations in LLMs2509.22711v1 · Divyanshu Kumar, Ishita Gupta, Nitin Aravind Birur et al.2025 · 0 citationsarXiv
No Free Lunch with Guardrails2504.00441v2 · Divyanshu Kumar, Nitin Aravind Birur, Tanay Baswa et al.2025 · 0 citationsarXiv
Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs2410.12864v1 · Divyanshu Kumar, Umang Jain, Sahil Agarwal et al.2024 · 5 citationsarXiv
VERA: Validation and Enhancement for Retrieval Augmented systems2409.15364v1 · Nitin Aravind Birur, Tanay Baswa, Divyanshu Kumar et al.2024 · 1 citationarXiv
SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming2408.11851v1 · Anurakt Kumar, Divyanshu Kumar, Jatan Loya et al.2024 · 0 citationsarXiv
Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes2404.04392v3 · Divyanshu Kumar, Anurakt Kumar, Sahil Agarwal et al.2024 · 3 citationsarXiv
Career total: 16 works. 12 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.