activity
20222026
most citedSoft Adversarial Training Can Retain Natural Accuracy

2 citations · 2 across the 4 of their papers we have counts for

collaborators

5 papers

cs.AI2026

PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents

Kshitij Mishra, Abhijith Sharma, Nils Lukas +1

Modern agentic systems extend language models with external tools, enabling them to complete complex tasks through multi-turn interactions. As these agents are deployed in conseque…

cs.CV2023

Assist Is Just as Important as the Goal: Image Resurfacing to Aid Model's Robust Prediction

Abhijith Sharma, Phil Munz, Apurva Narayan

Adversarial patches threaten visual AI models in the real world. The number of patches in a patch attack is variable and determines the attack's potency in a specific environment.…

cs.CV2023

NSA: Naturalistic Support Artifact to Boost Network Confidence

Abhijith Sharma, Phil Munz, Apurva Narayan

Visual AI systems are vulnerable to natural and synthetic physical corruption in the real-world. Such corruption often arises unexpectedly and alters the model's performance. In re…

cs.CV2022

Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey

Abhijith Sharma, Yijun Bian, Phil Munz +1

Adversarial attacks in deep learning models, especially for safety-critical systems, are gaining more and more attention in recent years, due to the lack of trust in the security a…

cs.LG2022★ 2 cited

Soft Adversarial Training Can Retain Natural Accuracy

Abhijith Sharma, Apurva Narayan

Adversarial training for neural networks has been in the limelight in recent years. The advancement in neural network architectures over the last decade has led to significant impr…