Related papers: Certifying Language Model Robustness with Fuzzed R…

Federated learning (FL) enables distributed model training across edge devices while preserving data locality. This decentralized approach has emerged as a promising solution for collaborative learning on sensitive user data, effectively…

Addressing the critical need for robust safety in Large Language Models (LLMs), particularly against adversarial attacks and in-distribution errors, we introduce Reinforcement Learning with Backtracking Feedback (RLBF). This framework…

Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive…

It is well-known that classifiers are vulnerable to adversarial perturbations. To defend against adversarial perturbations, various certified robustness results have been derived. However, existing certified robustnesses are limited to…

Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same…

Randomized smoothing is a technique for providing provable robustness guarantees against adversarial attacks while making minimal assumptions about a classifier. This method relies on taking a majority vote of any base classifier over…

Federated Learning (FL) offers a decentralized framework for training and fine-tuning Large Language Models (LLMs) by leveraging computational resources across organizations while keeping sensitive data on local devices. It addresses…

Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…

Multimodal large language models have become an important infrastructure for unified processing of visual and linguistic tasks. However, such models are highly susceptible to backdoor implantation during supervised fine-tuning and will…

The foundation models (FMs) have been used to generate synthetic public datasets for the heterogeneous federated learning (HFL) problem where each client uses a unique model architecture. However, the vulnerabilities of integrating FMs,…

Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods, primarily designed for classification tasks, are ineffective…

We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm. This "randomized smoothing" technique has been proposed…

The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…

Prompt-based tuning has emerged as a lightweight alternative to full fine-tuning in large vision-language models, enabling efficient adaptation via learned contextual prompts. This paradigm has recently been extended to federated learning…

Multimodal Diffusion Language Models (MDLMs) have recently emerged as a competitive alternative to their autoregressive counterparts. Yet their vulnerability to backdoor attacks remains largely unexplored. In this work, we show that…

Fine-tuning pre-trained language models (LMs) has become the de facto standard in many NLP tasks. Nevertheless, fine-tuned LMs are still prone to robustness issues, such as adversarial robustness and model calibration. Several perspectives…

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

We present a novel tool BertRLFuzzer, a BERT and Reinforcement Learning (RL) based fuzzer aimed at finding security vulnerabilities for Web applications. BertRLFuzzer works as follows: given a set of seed inputs, the fuzzer performs…

The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that…

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential…