302 citations · 947 across the 30 of their papers we have counts for
31 papers
From Alignment to Access Control: A Framework for GenAI Policy Enforcement
Nathalie Baracaldo
Generative AI (GenAI) applications have flourished enabling users to chat with large language models, and to create agents to act on their behalf for a variety of tasks. The pace o…
Granite.Trust Policy Tools: Shareable, Actionable Policies for Generative AI Applications
Nathalie Baracaldo, Nicolas Mello, Kush R. Varshney +3
When it comes to safety policies for generative AI, one size does not fit all. Each organization and use case needs to mitigate different risks depending on the application context…
Balancing Multi-modal Sensor Learning via Multi-objective Optimization
Heshan Fernando, Quan Xiao, Parikshit Ram +4
Learning-enabled control systems increasingly rely on multiple sensing modalities (e.g., vision, audio, language, etc.) for perception and decision support. A key challenge is that…
Towards a Re-evaluation of Data Forging Attacks in Practice
Mohamed Suliman, Anisa Halimi, Swanand Kadhe +2
Data forging attacks provide counterfactual proof that a model was trained on a given dataset, when in fact, it was trained on another. These attacks work by forging (replacing) mi…
MAP: Multi-Human-Value Alignment Palette
Xinran Wang, Qi Le, Ammar Ahmed +5
Ensuring that generative AI systems align with human values is essential but challenging, especially when considering multiple human values and their potential trade-offs. Since hu…
Understanding Forgetting in LLM Supervised Fine-Tuning and Preference Learning -- A Convex Optimization Perspective
Heshan Fernando, Han Shen, Parikshit Ram +4
The post-training of LLMs, which typically consists of the supervised fine-tuning (SFT) stage and the preference learning stage (RLHF or DPO), is crucial to effective and safe LLM…
Turning Generative Models Degenerate: The Power of Data Poisoning Attacks
Shuli Jiang, Swanand Ravindra Kadhe, Yi Zhou +3
The increasing use of large language models (LLMs) trained by third parties raises significant security concerns. In particular, malicious actors can introduce backdoors through po…
Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
Swanand Ravindra Kadhe, Farhan Ahmed, Dennis Wei +2
Large language models (LLMs) have shown to pose social and ethical risks such as generating toxic language or facilitating malicious use of hazardous knowledge. Machine unlearning…
Enhancing In-context Learning via Linear Probe Calibration
Momin Abbas, Yi Zhou, Parikshit Ram +4
In-context learning (ICL) is a new paradigm for natural language processing that utilizes Generative Pre-trained Transformer (GPT)-like models. This approach uses prompts that incl…
FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs
Swanand Ravindra Kadhe, Anisa Halimi, Ambrish Rawat +1
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 unsupervised pre-trainin…
Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks
Shuli Jiang, Swanand Ravindra Kadhe, Yi Zhou +2
Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious a…
Privacy-Preserving Federated Learning over Vertically and Horizontally Partitioned Data for Financial Anomaly Detection
Swanand Ravindra Kadhe, Heiko Ludwig, Nathalie Baracaldo +12
The effective detection of evidence of financial anomalies requires collaboration among multiple entities who own a diverse set of data, such as a payment network system (PNS) and…
LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning
Timothy Castiglia, Yi Zhou, Shiqiang Wang +3
We propose LESS-VFL, a communication-efficient feature selection method for distributed systems with vertically partitioned data. We consider a system of a server and several parti…
Federated XGBoost on Sample-Wise Non-IID Data
Katelinh Jones, Yuya Jeremy Ong, Yi Zhou +1
Federated Learning (FL) is a paradigm for jointly training machine learning algorithms in a decentralized manner which allows for parties to communicate with an aggregator to creat…
DeTrust-FL: Privacy-Preserving Federated Learning in Decentralized Trust Setting
Runhua Xu, Nathalie Baracaldo, Yi Zhou +3
Federated learning has emerged as a privacy-preserving machine learning approach where multiple parties can train a single model without sharing their raw training data. Federated…
Federated Unlearning: How to Efficiently Erase a Client in FL?
Anisa Halimi, Swanand Kadhe, Ambrish Rawat +1
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 training data. However, ex…
Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach
Nathalie Baracaldo, Ali Anwar, Mark Purcell +8
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 is promising regarding…
Single-shot Hyper-parameter Optimization for Federated Learning: A General Algorithm & Analysis
Yi Zhou, Parikshit Ram, Theodoros Salonidis +3
We address the relatively unexplored problem of hyper-parameter optimization (HPO) for federated learning (FL-HPO). We introduce Federated Loss SuRface Aggregation (FLoRA), a gener…
FLoRA: Single-shot Hyper-parameter Optimization for Federated Learning
Yi Zhou, Parikshit Ram, Theodoros Salonidis +3
We address the relatively unexplored problem of hyper-parameter optimization (HPO) for federated learning (FL-HPO). We introduce Federated Loss suRface Aggregation (FLoRA), the fir…
Privacy-Preserving Machine Learning: Methods, Challenges and Directions
Runhua Xu, Nathalie Baracaldo, James Joshi
Machine learning (ML) is increasingly being adopted in a wide variety of application domains. Usually, a well-performing ML model relies on a large volume of training data and high…
LEGATO: A LayerwisE Gradient AggregaTiOn Algorithm for Mitigating Byzantine Attacks in Federated Learning
Kamala Varma, Yi Zhou, Nathalie Baracaldo +1
Federated learning has arisen as a mechanism to allow multiple participants to collaboratively train a model without sharing their data. In these settings, participants (workers) m…
FedV: Privacy-Preserving Federated Learning over Vertically Partitioned Data
Runhua Xu, Nathalie Baracaldo, Yi Zhou +3
Federated learning (FL) has been proposed to allow collaborative training of machine learning (ML) models among multiple parties where each party can keep its data private. In this…
Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning
Syed Zawad, Ahsan Ali, Pin-Yu Chen +5
Data heterogeneity has been identified as one of the key features in federated learning but often overlooked in the lens of robustness to adversarial attacks. This paper focuses on…
Adaptive Histogram-Based Gradient Boosted Trees for Federated Learning
Yuya Jeremy Ong, Yi Zhou, Nathalie Baracaldo +1
Federated Learning (FL) is an approach to collaboratively train a model across multiple parties without sharing data between parties or an aggregator. It is used both in the consum…