相关论文: Here's a Free Lunch: Sanitizing Backdoored Models …

Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigger settings. To address this challenge, we propose…

Large language models (LLMs) have exhibited remarkable versatility and adaptability, while their widespread adoption across various applications also raises critical safety concerns. This paper focuses on the impact of backdoored LLMs.…

Large Language Models (LLMs) are known to be vulnerable to backdoor attacks, where triggers embedded in poisoned samples can maliciously alter LLMs' behaviors. In this paper, we move beyond attacking LLMs and instead examine backdoor…

Pre-trained Natural Language Processing (NLP) models can be easily adapted to a variety of downstream language tasks. This significantly accelerates the development of language models. However, NLP models have been shown to be vulnerable to…

Large language models (LLMs) have demonstrated superior performance compared to previous methods on various tasks, and often serve as the foundation models for many researches and services. However, the untrustworthy third-party LLMs may…

In a backdoor attack on a machine learning model, an adversary produces a model that performs well on normal inputs but outputs targeted misclassifications on inputs containing a small trigger pattern. Model compression is a widely-used…

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

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…

As ML models become increasingly complex and integral to high-stakes domains such as finance and healthcare, they also become more susceptible to sophisticated adversarial attacks. We investigate the threat posed by undetectable backdoors,…

Large-scale language models have achieved tremendous success across various natural language processing (NLP) applications. Nevertheless, language models are vulnerable to backdoor attacks, which inject stealthy triggers into models for…

Recent studies have pointed out that natural language processing (NLP) models are vulnerable to backdoor attacks. A backdoored model produces normal outputs on the clean samples while performing improperly on the texts with triggers that…

Fine-tuning large language models on private data for downstream applications poses significant privacy risks in potentially exposing sensitive information. Several popular community platforms now offer convenient distribution of a large…

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…

Existing studies in backdoor defense have predominantly focused on the training phase, overlooking the critical aspect of testing time defense. This gap becomes pronounced in the context of LLMs deployed as Web Services, which typically…

Diffusion models (DMs) are regarded as one of the most advanced generative models today, yet recent studies suggest that they are vulnerable to backdoor attacks, which establish hidden associations between particular input patterns and…

Recent studies have shown that deep neural networks (DNNs) are vulnerable to backdoor attacks, where a designed trigger is injected into the dataset, causing erroneous predictions when activated. In this paper, we propose a novel defense…

Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…

Model merging has emerged as a promising approach for updating large language models (LLMs) by integrating multiple domain-specific models into a cross-domain merged model. Despite its utility and plug-and-play nature, unmonitored mergers…

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) represents a novel paradigm to machine learning, addressing critical issues related to data privacy and security, yet suffering from data insufficiency and imbalance. The emergence of foundation models (FMs) provides…