相关论文: Adaptive Defense against Harmful Fine-Tuning for L…

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…

The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an…

This paper documents early research conducted in 2022 on defending against prompt injection attacks in large language models, providing historical context for the evolution of this critical security domain. This research focuses on two…

Fine-tuning large language models often undermines their safety alignment, a problem further amplified by harmful fine-tuning attacks in which adversarial data removes safeguards and induces unsafe behaviors. We propose SPARD, a defense…

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…

Existing language model safety evaluations focus on overt attacks and low-stakes tasks. In reality, an attacker can easily subvert existing safeguards by requesting help on small, benign-seeming tasks across many independent queries.…

Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often compromises their previously established safety alignment. To mitigate the degradation of model safety during fine-tuning, we introduce LookAhead…

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior of machine learning…

Federated learning (FL) enables multiple parties to collaboratively fine-tune an large language model (LLM) without the need of direct data sharing. Ideally, by training on decentralized data that is aligned with human preferences and…

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. Adversarial samples are crafted with a deliberate intention…

Adversarial attacks on deep-learning models pose a serious threat to their reliability and security. Existing defense mechanisms are narrow addressing a specific type of attack or being vulnerable to sophisticated attacks. We propose a new…

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

Machine learning based intrusion detection systems are increasingly targeted by black box adversarial attacks, where attackers craft evasive inputs using indirect feedback such as binary outputs or behavioral signals like response time and…

Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown that activating harmful-behavior modules during fine-tuning…

Determining the optimal data mixture for large language model training remains a challenging problem with an outsized impact on performance. In practice, language model developers continue to rely on heuristic exploration since no…

Current Large Language Models (LLMs), even those tuned for safety and alignment, are susceptible to jailbreaking. Some have found that just further fine-tuning an aligned model with benign data (i.e., data without harmful content)…

Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerability during this process, where malicious samples can…

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where an attacker manipulates a small portion of the training data to implant hidden backdoors into the model. The compromised model behaves normally on clean samples but…

Large Language Models (LLMs) pose a significant risk of safety misalignment after finetuning, as models can be compromised by both explicitly and implicitly harmful data. Even some seemingly benign data can inadvertently steer a model…