相关论文: Shortcuts Arising from Contrast: Effective and Cov…

Backdoor attacks in reinforcement learning (RL) have previously employed intense attack strategies to ensure attack success. However, these methods suffer from high attack costs and increased detectability. In this work, we propose a novel…

Audio-based machine learning systems frequently use public or third-party data, which might be inaccurate. This exposes deep neural network (DNN) models trained on such data to potential data poisoning attacks. In this type of assault,…

Deep neural networks usually require large labeled datasets for training to achieve state-of-the-art performance in many tasks, such as image classification and natural language processing. Although a lot of data is created each day by…

Chat template is a common technique used in the training and inference stages of Large Language Models (LLMs). It can transform input and output data into role-based and templated expressions to enhance the performance of LLMs. However,…

Backdoor attacks have become an emerging threat to NLP systems. By providing poisoned training data, the adversary can embed a "backdoor" into the victim model, which allows input instances satisfying certain textual patterns (e.g.,…

Backdoor unalignment attacks against Large Language Models (LLMs) enable the stealthy compromise of safety alignment using a hidden trigger while evading normal safety auditing. These attacks pose significant threats to the applications of…

Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to…

Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be…

Backdoor attacks significantly compromise the security of large language models by triggering them to output specific and controlled content. Currently, triggers for textual backdoor attacks fall into two categories: fixed-token triggers…

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be easily affected by…

Recently, backdoor attacks pose a new security threat to the training process of deep neural networks (DNNs). Attackers intend to inject hidden backdoors into DNNs, such that the attacked model performs well on benign samples, whereas its…

Whereas the recent emergence of large language models (LLMs) like ChatGPT has exhibited impressive general performance, it still has a large gap with fully-supervised models on specific tasks such as multi-span question answering. Previous…

Stealthy data poisoning during fine-tuning can backdoor large language models (LLMs), threatening downstream safety. Existing detectors either use classifier-style probability signals--ill-suited to generation--or rely on rewriting, which…

With the success of pre-trained visual-language (VL) models such as CLIP in visual representation tasks, transferring pre-trained models to downstream tasks has become a crucial paradigm. Recently, the prompt tuning paradigm, which draws…

Deep neural networks are vulnerable to backdoor attacks. Among the existing backdoor defense methods, trigger reverse engineering based approaches, which reconstruct the backdoor triggers via optimizations, are the most versatile and…

We study backdoor poisoning attacks against image classification networks, whereby an attacker inserts a trigger into a subset of the training data, in such a way that at test time, this trigger causes the classifier to predict some target…

We present a new perspective on the popular multi-class algorithmic techniques of one-vs-all and error correcting output codes. Rather than studying the behavior of these techniques for supervised learning, we establish a connection between…

Semi-supervised learning (SSL) addresses the lack of labeled data by exploiting large unlabeled data through pseudolabeling. However, in the extremely low-label regime, pseudo labels could be incorrect, a.k.a. the confirmation bias, and the…

We present SelfPrompt, a novel prompt-tuning approach for vision-language models (VLMs) in a semi-supervised learning setup. Existing methods for tuning VLMs in semi-supervised setups struggle with the negative impact of the miscalibrated…

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…