4 papers
IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks
Saikat Mondal, Mamta, Deeksha Varshney +2
Large language models (LLMs) are increasingly used in multilingual settings, yet their safety is still evaluated primarily in English. This limits our understanding of how alignmen…
MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models
Rishabh Makwana, Mamta, Deeksha Varshney +1
Vision-Language Models (VLMs) have demonstrated strong performance across multimodal tasks, yet their safety robustness remains an open challenge. While prior work has shown that s…
Concept-Based Interpretability for Toxicity Detection
Samarth Garg, Divya Singh, Deeksha Varshney +1
The rise of social networks has not only facilitated communication but also allowed the spread of harmful content. Although significant advances have been made in detecting toxic l…
Distraction-free Embeddings for Robust VQA
Atharvan Dogra, Deeksha Varshney, Ashwin Kalyan +2
The generation of effective latent representations and their subsequent refinement to incorporate precise information is an essential prerequisite for Vision-Language Understanding…