AIConfPaper
← Search

Krishnamurthy Dvijotham

11 accepted papers

2026

CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution

Minbeom Kim, Mihir Parmar, Phillip Wallis, Lesly Miculicich, Kyomin Jung, Krishnamurthy Dvijotham +2
ICML 2026poster

AI agents equipped with tool-calling capabilities are susceptible to *Indirect Prompt Injection* (IPI) attacks. In this attack scenario, malicious commands hidden within *untrusted* content trick the agent into performing unauthorized actions. Existing defenses can reduce attack success but often su…

Cited by 0Source ↗Scholar ↗
2026

Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG

Sarthak Choudhary, Nils Palumbo, Ashish Hooda, Krishnamurthy Dvijotham, Somesh Jha
ICML 2026poster

Retrieval-augmented generation (RAG) systems are vulnerable to attacks that inject poisoned passages into the retrieved context, even at low corruption rates. We show that existing attacks are not designed to be stealthy, allowing reliable detection and mitigation. We formalize a distinguishability-…

Cited by 0Source ↗Scholar ↗
2023

Interactive Concept Bottleneck Models

Kushal Chauhan, Rishabh Tiwari, Jan Freyberg, Pradeep Shenoy, Krishnamurthy Dvijotham
AAAI 2023technical

Concept bottleneck models (CBMs) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then predict the final label based on the concept label predictions. We extend CBMs to interactive prediction settings where the model ca…

Cited by 65Source ↗PDF ↗code ↗Scholar ↗
2022

Role of Human-AI Interaction in Selective Prediction

Elizabeth Bondi, Raphael Koster, Hannah Sheahan, Martin Chadwick, Yoram Bachrach, Taylan Cemgil +2
AAAI 2022technical

Recent work has shown the potential benefit of selective prediction systems that can learn to defer to a human when the predictions of the AI are unreliable, particularly to improve the reliability of AI systems in high-stakes applications like healthcare or conservation. However, most prior work a…

Cited by 53Source ↗PDF ↗code ↗Scholar ↗
2020

Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations

Sven Gowal, Chongli Qin, Po-Sen Huang, Taylan Cemgil, Krishnamurthy Dvijotham, Timothy Mann +1
CVPR 2020poster

Recent research has made the surprising finding that state-of-the-art deep learning models sometimes fail to generalize to small variations of the input. Adversarial training has been shown to be an effective approach to overcome this problem. However, its application has been limited to enforcing i…

Cited by 67PDF ↗code ↗Scholar ↗
2020

An efficient nonconvex reformulation of stagewise convex optimization problems

Rudy R Bunel, Oliver Hinder, Srinadh Bhojanapalli, Krishnamurthy Dvijotham
NeurIPS 2020poster

Convex optimization problems with staged structure appear in several contexts, including optimal control, verification of deep neural networks, and isotonic regression. Off-the-shelf solvers can solve these problems but may scale poorly. We develop a nonconvex reformulation designed to exploit this…

Cited by 20Source ↗PDF ↗Scholar ↗
2020

Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

Sumanth Dathathri, Krishnamurthy Dvijotham, Alexey Kurakin, Aditi Raghunathan, Jonathan Uesato, Rudy R Bunel +5
NeurIPS 2020poster

Convex relaxations have emerged as a promising approach for verifying properties of neural networks, but widely used using Linear Programming (LP) relaxations only provide meaningful certificates when networks are specifically trained to facilitate verification. This precludes many important applica…

Cited by 130Source ↗PDF ↗code ↗Scholar ↗
2020

Lagrangian Decomposition for Neural Network Verification

Rudy Bunel, Alessandro De Palma, Alban Desmaison, Krishnamurthy Dvijotham, Pushmeet Kohli, Philip Torr +1
UAI 2020poster

A fundamental component of neural network verification is the computation of bounds on the values their outputs can take. Previous methods have either used off-the-shelf solvers, discarding the problem structure, or relaxed the problem even further, making the bounds unnecessarily loose. We propose…

Cited by 65Source ↗PDF ↗code ↗Scholar ↗
2020

The Autoencoding Variational Autoencoder

Taylan Cemgil, Sumedh Ghaisas, Krishnamurthy Dvijotham, Sven Gowal, Pushmeet Kohli
NeurIPS 2020spotlight

Does a Variational AutoEncoder (VAE) consistently encode typical samples generated from its decoder? This paper shows that the perhaps surprising answer to this question is `No'; a (nominally trained) VAE does not necessarily amortize inference for typical samples that it is capable of generating. W…

Cited by 0Source ↗PDF ↗Scholar ↗
2019

Adversarial Robustness through Local Linearization

Chongli Qin, James Martens, Sven Gowal, Dilip Krishnan, Krishnamurthy Dvijotham, Alhussein Fawzi +3
NeurIPS 2019poster

Adversarial training is an effective methodology for training deep neural networks that are robust against adversarial, norm-bounded perturbations. However, the computational cost of adversarial training grows prohibitively as the size of the model and number of input dimensions increase. Further, t…

Cited by 367Source ↗PDF ↗Scholar ↗
2019

Knowing When to Stop: Evaluation and Verification of Conformity to Output-Size Specifications

Chenglong Wang, Rudy Bunel, Krishnamurthy Dvijotham, Po-Sen Huang, Edward Grefenstette, Pushmeet Kohli
CVPR 2019poster

Neural architectures able to generate variable-length outputs are extremely effective for applications like Machine Translation and Image Captioning. In this paper, we study the vulnerability of these models to attacks aimed at changing the output-size that can have undesirable consequences includin…

Cited by 13PDF ↗Scholar ↗