Shravya Kanchi

Shravya Kanchi

Auto-generated profile, based on publicly available information

Shravya Kanchi

Virginia Tech, Blacksburg, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 December 2023
Verified
Conference Paper
Open access
CWConnor Weeks
Connor Weeks
ACAravind Cheruvu
Aravind Cheruvu
SASifat Muhammad Abdullah
Sifat Muhammad Abdullah
SKShravya Kanchi
Shravya Kanchi
DYDaphne Yao
Daphne Yao
BVBimal Viswanath
Bimal Viswanath
Chatbot systems have improved significantly because of the advances made in language modeling. These machine learning systems follow an end-to-end data-driven learning paradigm and are trained on large conversational datasets. Imperfections or harmful biases in the training datasets can cause the models to learn toxic behavior, and thereby expose their users to harmful responses. Prior work has focused on measuring the inherent toxicity of such chatbots, by devising queries that are more likely to produce toxic responses. In this work, we ask the question: How easy or hard is it to inject toxicity into a chatbot after deployment? We study this in a practical scenario known as Dialog-based Learning (DBL), where a chatbot is periodically trained on recent conversations with its users after deployment. A DBL setting can be exploited to poison the training dataset for each training cycle. Our attacks would allow an adversary to manipulate the degree of toxicity in a model and also enable control over what type of queries can trigger a toxic response. Our fully automated attacks only require LLM-based software agents masquerading as (malicious) users to inject high levels of toxicity. We systematically explore the vulnerability of popular chatbot pipelines to this threat. Lastly, we show that several existing toxicity mitigation strategies (designed for chatbots) can be significantly weakened by adaptive attackers.

4 June 2026
Verified
Conference Paper
Open access
SKShravya Kanchi
Shravya Kanchi
NMNeal Mangaokar
Neal Mangaokar
ACAravind Cheruvu
Aravind Cheruvu
SASifat Muhammad Abdullah
Sifat Muhammad Abdullah
SNShirin Nilizadeh
Shirin Nilizadeh
BVBimal Viswanath
Bimal Viswanath

22 June 2026
Verified
Conference Paper
Open access
ACAravind Cheruvu
Aravind Cheruvu
SKShravya Kanchi
Shravya Kanchi
SASifat Muhammad Abdullah
Sifat Muhammad Abdullah
NKNicholas Ka-Shing Kong
Nicholas Ka-Shing Kong
DYDaphne Yao
Daphne Yao
BVBimal Viswanath
Bimal Viswanath