Related papers: LoRA as Oracle

Low-Rank Adaptation (LoRA) is one of the most widely used techniques for fine-tuning large language models (LLMs). By introducing a small number of trainable low-rank weight matrices, LoRA substantially reduces the number of parameters that…

Large Language Models (LLMs) have the promise to revolutionize computing broadly, but their complexity and extensive training data also expose significant privacy vulnerabilities. One of the simplest privacy risks associated with LLMs is…

Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…

Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of…

Fine-tuning large vision models (LVMs) and large language models (LLMs) under differentially private federated learning (DPFL) is hindered by a fundamental privacy-utility trade-off. Low-Rank Adaptation (LoRA), a promising…

How to adapt a pre-trained model continuously for sequential tasks with different prediction class labels and domains and finally learn a generalizable model across diverse tasks is a long-lasting challenge. Continual learning (CL) has…

In recent years, enterprises have been targeted by advanced adversaries who leverage creative ways to infiltrate their systems and move laterally to gain access to critical data. One increasingly common evasive method is to hide the…

Low-rank adapation (LoRA) is a popular method that reduces the number of trainable parameters when finetuning large language models, but still faces acute storage challenges when scaling to even larger models or deploying numerous per-user…

Machine Learning (ML) has made unprecedented progress in the past several decades. However, due to the memorability of the training data, ML is susceptible to various attacks, especially Membership Inference Attacks (MIAs), the objective of…

Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning (PEFT) method validated across NLP and CV domains. However, LoRA faces an inherent low-rank bottleneck: narrowing its performance gap with full finetuning…

Backdoor attacks are dangerous and difficult to prevent in federated learning (FL), where training data is sourced from untrusted clients over long periods of time. These difficulties arise because: (a) defenders in FL do not have access to…

This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on elusive in-distribution backdoor triggers. Such triggers…

Recent studies have demonstrated the susceptibility of deep neural networks to backdoor attacks. Given a backdoored model, its prediction of a poisoned sample with trigger will be dominated by the trigger information, though trigger…

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

In this paper, we address the challenge of detecting hateful memes in the low-resource setting where only a few labeled examples are available. Our approach leverages the compositionality of Low-rank adaptation (LoRA), a widely used…

The usage of deep learning is being escalated in many applications. Due to its outstanding performance, it is being used in a variety of security and privacy-sensitive areas in addition to conventional applications. One of the key aspects…

The rise of API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods to identify model vulnerabilities in real-world settings. Without a principled objective for gradient-based optimization,…

Federated Learning is a machine learning setting that reduces direct data exposure, improving the privacy guarantees of machine learning models. Yet, the exchange of model updates between the participants and the aggregator can still leak…

Deep neural networks (DNNs) have shown unprecedented success in object detection tasks. However, it was also discovered that DNNs are vulnerable to multiple kinds of attacks, including Backdoor Attacks. Through the attack, the attacker…

As machine learning (ML) systems are being increasingly employed in the real world to handle sensitive tasks and make decisions in various fields, the security and privacy of those models have also become increasingly critical. In…