Search Results for author:
Found 30 papers, 8 papers with code
Activated LoRA: Fine-tuned LLMs for Intrinsics
This change crucially allows aLoRA to accept the base model's KV cache of the input string, meaning that aLoRA can be instantly activated whenever needed in a chain without recomputing the cache.
MAD-MAX: Modular And Diverse Malicious Attack MiXtures for Automated LLM Red Teaming
The MAD-MAX approach is designed to be easily extensible with newly discovered attack strategies and outperforms the prominent Red Teaming method Tree of Attacks with Pruning (TAP) significantly in terms of Attack Success Rate (ASR) and queries needed to achieve jailbreaks.
Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs
We find that there is significant performance variation depending on the style of jailbreak a defence is subject to.
Granite Guardian
We introduce the Granite Guardian models, a suite of safeguards designed to provide risk detection for prompts and responses, enabling safe and responsible use in combination with any large language model (LLM).
Attention Tracker: Detecting Prompt Injection Attacks in LLMs
Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring original instructions and executing designated action.
MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks
The proliferation of Large Language Models (LLMs) in diverse applications underscores the pressing need for robust security measures to thwart potential jailbreak attacks.
Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI
As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and multi-modal systems.
Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations.
Domain Adaptation for Time series Transformers using One-step fine-tuning
To address these limitations, in this paper, we pre-train the time series Transformer model on a source domain with sufficient data and fine-tune it on the target domain with limited data.
FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs
We evaluate the performance-fairness trade-off for SISA, and empirically demsontrate that SISA can indeed reduce fairness in LLMs.
Privacy-Preserving Federated Learning over Vertically and Horizontally Partitioned Data for Financial Anomaly Detection
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 its partner banks.
Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models
The wide applicability and adaptability of generative large language models (LLMs) has enabled their rapid adoption.
Robust Learning Protocol for Federated Tumor Segmentation Challenge
In this work, we devise robust and efficient learning protocols for orchestrating a Federated Learning (FL) process for the Federated Tumor Segmentation Challenge (FeTS 2022).
Federated Unlearning: How to Efficiently Erase a Client in FL?
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.
Challenges and Pitfalls of Bayesian Unlearning
Machine unlearning refers to the task of removing a subset of training data, thereby removing its contributions to a trained model.
Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach
Federated Learning (FL) is a novel paradigm for the shared training of models based on decentralized and private data.
Certified Federated Adversarial Training
We model an attacker who poisons the model to insert a weakness into the adversarial training such that the model displays apparent adversarial robustness, while the attacker can exploit the inserted weakness to bypass the adversarial training and force the model to misclassify adversarial examples.
Automated Robustness with Adversarial Training as a Post-Processing Step
Adversarial training is a computationally expensive task and hence searching for neural network architectures with robustness as the criterion can be challenging.
The Devil is in the GAN: Backdoor Attacks and Defenses in Deep Generative Models
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, high-dimensional manifolds.
Bandit Limited Discrepancy Search and Application to Machine Learning Pipeline Optimization
Optimizing a machine learning (ML) pipeline has been an important topic of AI and ML.
FAT: Federated Adversarial Training
Federated learning (FL) is one of the most important paradigms addressing privacy and data governance issues in machine learning (ML).
IBM Federated Learning: an Enterprise Framework White Paper V0.1
Federated Learning (FL) is an approach to conduct machine learning without centralizing training data in a single place, for reasons of privacy, confidentiality or data volume.
How can AI Automate End-to-End Data Science?
Data science is labor-intensive and human experts are scarce but heavily involved in every aspect of it.
A Survey on Neural Architecture Search
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 for neural architecture search.
Adversarial Robustness Toolbox v1.0.0
Defending Machine Learning models involves certifying and verifying model robustness and model hardening with approaches such as pre-processing inputs, augmenting training data with adversarial samples, and leveraging runtime detection methods to flag any inputs that might have been modified by an adversary.
Scalable Multi-Class Bayesian Support Vector Machines for Structured and Unstructured Data
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 mixture of Gaussians.
Adversarial Phenomenon in the Eyes of Bayesian Deep Learning
Deep Learning models are vulnerable to adversarial examples, i. e.\ images obtained via deliberate imperceptible perturbations, such that the model misclassifies them with high confidence.
Open-World Visual Recognition Using Knowledge Graphs
First, a knowledge-graph representation is learned to embed a large set of entities into a semantic space.
Efficient Defenses Against Adversarial Attacks
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 indisputable threat.
Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network training
Generative Adversarial Networks (GANs) have become a widely popular framework for generative modelling of high-dimensional datasets.
