SK

Shravya Kanchi

0009-0005-4088-8408

cs.CRcs.AIcs.LGcs.CLcs.CVcs.SE

On Valency

published · living versions

W_qy3a7k9h·v1 · currentpublished

Permitted but Unauthorized: Affordance-Induced Delegated-Scope Violations in Multi-Agent LLM Systems

1 version

Preprints & journals

4 papers in the corpus · 2024–2026

Generating Proof-of-Vulnerability Tests to Help Enhance the Security of Complex Software2605.03956v1 · Shravya Kanchi, Xiaoyan Zang, Ying Zhang et al.2026 · 0 citationsarXiv

Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI2507.05660v3 · Aravind Cheruvu, Shravya Kanchi, Sifat Muhammad Abdullah et al.2025 · 0 citationsarXiv

Taming Data Challenges in ML-based Security Tasks Using Generative AI2507.06092v4 · Shravya Kanchi, Neal Mangaokar, Aravind Cheruvu et al.2025 · 0 citationsIn Proc. ACM AsiaCCS 2026, Bangalore, India, June 1-5, 2026. ACM, 2026

An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscape2404.16212v1 · Sifat Muhammad Abdullah, Aravind Cheruvu, Shravya Kanchi et al.2024 · 38 citationsarXiv

Career total: 8 works. 4 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.