相关论文: Efficient Backdoor Defense in Multimodal Contrasti…

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

A backdoor or Trojan attack is an important type of data poisoning attack against deep neural network (DNN) classifiers, wherein the training dataset is poisoned with a small number of samples that each possess the backdoor pattern (usually…

Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned examples into the training dataset. While extensive efforts have been…

Language models can retain dangerous knowledge and skills even after extensive safety fine-tuning, posing both misuse and misalignment risks. Recent studies show that even specialized unlearning methods can be easily reversed. To address…

In this brief, we show that sequentially learning new information presented to a continual (incremental) learning model introduces new security risks: an intelligent adversary can introduce small amount of misinformation to the model during…

As a novel privacy-preserving paradigm aimed at reducing client computational costs and achieving data utility, split learning has garnered extensive attention and proliferated widespread applications across various fields, including smart…

Pre-trained language models allowed us to process downstream tasks with the help of fine-tuning, which aids the model to achieve fairly high accuracy in various Natural Language Processing (NLP) tasks. Such easily-downloaded language models…

Recently, backdoor attacks have become an emerging threat to the security of machine learning models. From the adversary's perspective, the implanted backdoors should be resistant to defensive algorithms, but some recently proposed…

Modern machine learning (ML) systems demand substantial training data, often resorting to external sources. Nevertheless, this practice renders them vulnerable to backdoor poisoning attacks. Prior backdoor defense strategies have primarily…

In recent years, there has been an explosive growth in multimodal learning. Image captioning, a classical multimodal task, has demonstrated promising applications and attracted extensive research attention. However, recent studies have…

Deep neural networks for image classification are well-known to be vulnerable to adversarial attacks. One such attack that has garnered recent attention is the adversarial backdoor attack, which has demonstrated the capability to perform…

Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models (LLMs) while preserving overall performance. We propose an inference-time unlearning algorithm that uses contrastive…

Large Language Models (LLMs) are known to be vulnerable to jailbreak attacks. An important observation is that, while different types of jailbreak attacks can generate significantly different queries, they mostly result in similar responses…

As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy…

Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. However, a major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression, a…

Backdoor attacks are an important type of adversarial threat against deep neural network classifiers, wherein test samples from one or more source classes will be (mis)classified to the attacker's target class when a backdoor pattern is…

Federated learning enables training high-utility models across several clients without directly sharing their private data. As a downside, the federated setting makes the model vulnerable to various adversarial attacks in the presence of…

Multimodal recommender systems exploit visual and textual signals to alleviate data sparsity, but this also makes them more vulnerable to evasion-based promotion attacks. Existing defenses are largely limited to single-modal settings and…

It is common practice to outsource the training of machine learning models to cloud providers. Clients who do so gain from the cloud's economies of scale, but implicitly assume trust: the server should not deviate from the client's training…

Large language model (LLM) unlearning aims to remove specific data influences from pre-trained model without costly retraining, addressing privacy, copyright, and safety concerns. However, recent studies reveal a critical vulnerability:…