Search Results - "Rawat, Ambrish"

FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs by Kadhe, Swanand Ravindra, Halimi, Anisa, Rawat, Ambrish, Baracaldo, Nathalie

“…Training large language models (LLMs) is a costly endeavour in terms of time and computational resources. The large amount of training data used during the…”
Get full text

Automated Robustness with Adversarial Training as a Post-Processing Step by Rawat, Ambrish, Sinn, Mathieu, Buesser, Beat

“…Adversarial training is a computationally expensive task and hence searching for neural network architectures with robustness as the criterion can be…”
Get full text

Scalable Multi-Class Bayesian Support Vector Machines for Structured and Unstructured Data by Wistuba, Martin, Rawat, Ambrish

“…We introduce a new Bayesian multi-class support vector machine by formulating a pseudo-likelihood for a multi-class hinge loss in the form of a location-scale…”
Get full text

The Devil is in the GAN: Backdoor Attacks and Defenses in Deep Generative Models by Rawat, Ambrish, Levacher, Killian, Sinn, Mathieu

“…Deep Generative Models (DGMs) are a popular class of deep learning models which find widespread use because of their ability to synthesize data from complex,…”
Get full text

MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks by Cornacchia, Giandomenico, Zizzo, Giulio, Fraser, Kieran, Hameed, Muhammad Zaid, Rawat, Ambrish, Purcell, Mark

“…The proliferation of Large Language Models (LLMs) in diverse applications underscores the pressing need for robust security measures to thwart potential…”
Get full text

Federated Unlearning: How to Efficiently Erase a Client in FL? by Halimi, Anisa, Kadhe, Swanand, Rawat, Ambrish, Baracaldo, Nathalie

“…With privacy legislation empowering the users with the right to be forgotten, it has become essential to make a model amenable for forgetting some of its…”
Get full text

Challenges and Pitfalls of Bayesian Unlearning by Rawat, Ambrish, Requeima, James, Bruinsma, Wessel, Turner, Richard

“…Machine unlearning refers to the task of removing a subset of training data, thereby removing its contributions to a trained model. Approximate unlearning are…”
Get full text

Domain Adaptation for Time series Transformers using One-step fine-tuning by Khanal, Subina, Tirupathi, Seshu, Zizzo, Giulio, Rawat, Ambrish, Pedersen, Torben Bach

“…The recent breakthrough of Transformers in deep learning has drawn significant attention of the time series community due to their ability to capture…”
Get full text

Attention Tracker: Detecting Prompt Injection Attacks in LLMs by Hung, Kuo-Han, Ko, Ching-Yun, Rawat, Ambrish, Chung, I-Hsin, Hsu, Winston H, Chen, Pin-Yu

“…Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model…”
Get full text

Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network training by Sinn, Mathieu, Rawat, Ambrish

“…Generative Adversarial Networks (GANs) have become a widely popular framework for generative modelling of high-dimensional datasets. However their training is…”
Get full text

Certified Federated Adversarial Training by Zizzo, Giulio, Rawat, Ambrish, Sinn, Mathieu, Maffeis, Sergio, Hankin, Chris

“…In federated learning (FL), robust aggregation schemes have been developed to protect against malicious clients. Many robust aggregation schemes rely on…”
Get full text

Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models by Foley, Myles, Rawat, Ambrish, Lee, Taesung, Hou, Yufang, Picco, Gabriele, Zizzo, Giulio

“…The wide applicability and adaptability of generative large language models (LLMs) has enabled their rapid adoption. While the pre-trained models can perform…”
Get full text

Robust Learning Protocol for Federated Tumor Segmentation Challenge by Rawat, Ambrish, Zizzo, Giulio, Kadhe, Swanand, Epperlein, Jonathan P, Braghin, Stefano

“…In this work, we devise robust and efficient learning protocols for orchestrating a Federated Learning (FL) process for the Federated Tumor Segmentation…”
Get full text

A Survey on Neural Architecture Search by Wistuba, Martin, Rawat, Ambrish, Pedapati, Tejaswini

“…The growing interest in both the automation of machine learning and deep learning has inevitably led to the development of a wide variety of automated methods…”
Get full text

FAT: Federated Adversarial Training by Zizzo, Giulio, Rawat, Ambrish, Sinn, Mathieu, Buesser, Beat

“…Federated learning (FL) is one of the most important paradigms addressing privacy and data governance issues in machine learning (ML). Adversarial training has…”
Get full text

Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI by Rawat, Ambrish, Schoepf, Stefan, Zizzo, Giulio, Cornacchia, Giandomenico, Hameed, Muhammad Zaid, Fraser, Kieran, Miehling, Erik, Buesser, Beat, Daly, Elizabeth M, Purcell, Mark, Sattigeri, Prasanna, Chen, Pin-Yu, Varshney, Kush R

“…As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and…”
Get full text

Adversarial Phenomenon in the Eyes of Bayesian Deep Learning by Rawat, Ambrish, Wistuba, Martin, Nicolae, Maria-Irina

“…Deep Learning models are vulnerable to adversarial examples, i.e.\ images obtained via deliberate imperceptible perturbations, such that the model…”
Get full text

Privacy-Preserving Federated Learning over Vertically and Horizontally Partitioned Data for Financial Anomaly Detection by Kadhe, Swanand Ravindra, Ludwig, Heiko, Baracaldo, Nathalie, King, Alan, Zhou, Yi, Houck, Keith, Rawat, Ambrish, Purcell, Mark, Holohan, Naoise, Takeuchi, Mikio, Kawahara, Ryo, Drucker, Nir, Shaul, Hayim, Kushnir, Eyal, Soceanu, Omri

“…The effective detection of evidence of financial anomalies requires collaboration among multiple entities who own a diverse set of data, such as a payment…”
Get full text

Efficient Defenses Against Adversarial Attacks by Zantedeschi, Valentina, Nicolae, Maria-Irina, Rawat, Ambrish

“…Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an…”
Get full text

Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach by Baracaldo, Nathalie, Anwar, Ali, Purcell, Mark, Rawat, Ambrish, Sinn, Mathieu, Altakrouri, Bashar, Balta, Dian, Sellami, Mahdi, Kuhn, Peter, Schopp, Ulrich, Buchinger, Matthias

“…Federated Learning (FL) is a novel paradigm for the shared training of models based on decentralized and private data. With respect to ethical guidelines, FL…”
Get full text