Ranganath Krishnan — accepted AI-conference papers

2026

EigenShield: Inference-Time, Model-Agnostic Jailbreaking Defense via Causal Subspace Filtering

Nastaran Darabi, Devashri Naik, Sina Tayebati, Dinithi Jayasuriya, Ranganath Krishnan, Amit Ranjan Trivedi

AAAI 2026technical

Large Language Models (LLMs) and Vision-Language Models (VLMs) remain highly vulnerable to adversarial attacks despite widespread adoption. Existing defenses typically require retraining, rely on heuristics, or fail under adaptive and out-of-distribution (OOD) conditions. We introduce EigenShield, a

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Learnable Conformal Prediction for Safe and Efficient Robotics under Perception and Planning Uncertainties

Divake Kumar, Sina Tayebati, Francesco Migliarba, Ranganath Krishnan, Amit Ranjan Trivedi

ICRA 2026poster

Deep learning models in robotics often output point estimates with poorly calibrated confidences, offering no native mechanism to quantify predictive reliability under novel, noisy, or out-of-distribution inputs. Conformal prediction (CP) addresses this gap by providing distribution-free coverage gu…

Cited by 0 Scholar ↗

2026

TRACER: Trajectory Risk Aggregation for Critical Episodes in Agentic Reasoning

Sina Tayebati, Divake Kumar, Nastaran Darabi, Davide Ettori, Ranganath Krishnan, Amit Trivedi

ICML 2026poster

Estimating uncertainty for AI agents in real-world multi-turn tool-using interaction with humans is difficult because failures are often triggered by sparse critical episodes (e.g., looping, incoherent tool use, or user-agent miscoordination) even when local generation appears confident. Existing un…

Cited by 0 Source ↗Scholar ↗

2020

Improving model calibration with accuracy versus uncertainty optimization

Ranganath Krishnan, Omesh Tickoo

NeurIPS 2020poster

Obtaining reliable and accurate quantification of uncertainty estimates from deep neural networks is important in safety-critical applications. A well-calibrated model should be accurate when it is certain about its prediction and indicate high uncertainty when it is likely to be inaccurate. Uncerta…

Cited by 215 Source ↗PDF ↗code ↗Scholar ↗

2019

Uncertainty-Aware Audiovisual Activity Recognition Using Deep Bayesian Variational Inference

Mahesh Subedar, Ranganath Krishnan, Paulo Lopez Meyer, Omesh Tickoo, Jonathan Huang

ICCV 2019oral

Deep neural networks (DNNs) provide state-of-the-art results for a multitude of applications, but the approaches using DNNs for multimodal audiovisual applications do not consider predictive uncertainty associated with individual modalities. Bayesian deep learning methods provide principled confiden…

Cited by 89 PDF ↗Scholar ↗