3 papers
cs.CL2026
Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention
Himanshu Singh, Ziwei Xu, A. V. Subramanyam +1
Large Language Models (LLMs) are powerful text generators, yet they can produce toxic or harmful content even when given seemingly harmless prompts. This presents a serious safety…
cs.CV2025
Nearest Neighbor Projection Removal Adversarial Training
Himanshu Singh, A. V. Subramanyam, Shivank Rajput +1
Deep neural networks have exhibited impressive performance in image classification tasks but remain vulnerable to adversarial examples. Standard adversarial training enhances robus…
cs.LG2023
Language Guided Adversarial Purification
Himanshu Singh, A V Subramanyam
Adversarial purification using generative models demonstrates strong adversarial defense performance. These methods are classifier and attack-agnostic, making them versatile but of…