Related papers: Concept-Guided Backdoor Attack on Vision Language …

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…

Pre-trained vision models (PVMs) have become a dominant component due to their exceptional performance when fine-tuned for downstream tasks. However, the presence of backdoors within PVMs poses significant threats. Unfortunately, existing…

Due to the high cost of training, large model (LM) practitioners commonly use pretrained models downloaded from untrusted sources, which could lead to owning compromised models. In-context learning is the ability of LMs to perform multiple…

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

The Large Language Models (LLMs) are poised to offer efficient and intelligent services for future mobile communication networks, owing to their exceptional capabilities in language comprehension and generation. However, the extremely high…

Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…

Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has…

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,…

Instruction tuning enhances large vision-language models (LVLMs) but increases their vulnerability to backdoor attacks due to their open design. Unlike prior studies in static settings, this paper explores backdoor attacks in LVLM…

Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…

Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into…

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…

Although Deep Neural Network (DNN) has led to unprecedented progress in various natural language processing (NLP) tasks, research shows that deep models are extremely vulnerable to backdoor attacks. The existing backdoor attacks mainly…

The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol…

Large Vision-Language Models (LVLMs) are susceptible to typographic attacks, which are misclassifications caused by an attack text that is added to an image. In this paper, we introduce a multi-image setting for studying typographic…

Vision-Language Models (VLMs) have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However, securing these models against jailbreak attacks continues to be a substantial challenge.…

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…

We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstrate new classes of backdoors strictly more powerful than…